| Thinking - Fast, Slow, and Artificial: How AI is Reshaping Human Reasoning and the Rise of Cognitive Surrender | Governance and Policy | Trust and Adoption |
| The Universal Cloud Threat Model | Threat Modeling | Threat Models |
| New prompt injection papers: Agents Rule of Two and The Attacker Moves Second | Prompt Injection | Prompt Injection Research |
| Call for Papers | Prompt Injection | Prompt Injection General |
| Supply Chain Reaction: Enhancing the Precision of Vulnerability Triage using Code Reachability Information | Supply Chain | Resources |
| Chainguard OS Whitepaper | Sandboxing and Isolation | Containerization |
| Defending against Indirect Prompt Injection by Instruction Detection | Papers | Prompt Injection and Jailbreaking |
| Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment | Papers | Prompt Injection and Jailbreaking |
| PromptSleuth: Detecting Prompt Injection via Semantic Intent Invariance | Papers | Prompt Injection and Jailbreaking |
| EchoLeak: The First Real-World Zero-Click Prompt Injection Exploit in a Production LLM System | Papers | Prompt Injection and Jailbreaking |
| Jailbreaking Large Language Models Through Content Concretization | Papers | Prompt Injection and Jailbreaking |
| Visual Contextual Attack: Jailbreaking MLLMs with Image-Driven Context Injection | Papers | Prompt Injection and Jailbreaking |
| When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review | Papers | Prompt Injection and Jailbreaking |
| Decoding Latent Attack Surfaces in LLMs: Prompt Injection via HTML in Web Summarization | Papers | Prompt Injection and Jailbreaking |
| Multimodal Prompt Injection Attacks: Risks and Defenses for Modern LLMs | Papers | Prompt Injection and Jailbreaking |
| Between a Rock and a Hard Place: Exploiting Ethical Reasoning to Jailbreak LLMs | Papers | Prompt Injection and Jailbreaking |
| Behind the Mask: Benchmarking Camouflaged Jailbreaks in Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Breaking to Build: A Threat Model of Prompt-Based Attacks for Securing LLMs | Papers | Prompt Injection and Jailbreaking |
| Prompt-in-Content Attacks: Exploiting Uploaded Inputs to Hijack LLM Behavior | Papers | Prompt Injection and Jailbreaking |
| Involuntary Jailbreak: On Self-Prompting Attacks | Papers | Prompt Injection and Jailbreaking |
| Mitigating Jailbreaks with Intent-Aware LLMs | Papers | Prompt Injection and Jailbreaking |
| When Memory Becomes a Vulnerability: Towards Multi-turn Jailbreak Attacks against Text-to-Image Generation Systems | Papers | Prompt Injection and Jailbreaking |
| Publish to Perish: Prompt Injection Attacks on LLM-Assisted Peer Review | Papers | Prompt Injection and Jailbreaking |
| Probabilistic Modeling of Jailbreak on Multimodal LLMs: From Quantification to Application | Papers | Prompt Injection and Jailbreaking |
| SATA: A Paradigm for LLM Jailbreak via Simple Assistive Task Linkage | Papers | Prompt Injection and Jailbreaking |
| Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Jailbroken: How Does LLM Safety Training Fail? | Papers | Prompt Injection and Jailbreaking |
| Using Hallucinations to Bypass GPT4's Filter | Papers | Prompt Injection and Jailbreaking |
| Hijacking Large Language Models via Adversarial In-Context Learning | Papers | Prompt Injection and Jailbreaking |
| TombRaider: Entering the Vault of History to Jailbreak Large Language Models | Papers | Prompt Injection and Jailbreaking |
| PiCo: Jailbreaking Multimodal Large Language Models via Pictorial Code Contextualization | Papers | Prompt Injection and Jailbreaking |
| BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage | Papers | Prompt Injection and Jailbreaking |
| Chain-of-Jailbreak Attack for Image Generation Models via Editing Step by Step | Papers | Prompt Injection and Jailbreaking |
| AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs | Papers | Prompt Injection and Jailbreaking |
| Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models | Papers | Prompt Injection and Jailbreaking |
| PRISON: Unmasking the Criminal Potential of Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Defeating Prompt Injections by Design | Papers | Prompt Injection and Jailbreaking |
| Prompt Inversion Attack against Collaborative Inference of Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Cybersecurity AI: Hacking the AI Hackers via Prompt Injection | Papers | Prompt Injection and Jailbreaking |
| Defending Against Prompt Injection With a Few Defensive Tokens | Papers | Prompt Injection and Jailbreaking |
| Design Patterns for Securing LLM Agents against Prompt Injections | Papers | Prompt Injection and Jailbreaking |
| Prompt Stealing Attacks Against Large Language Models | Papers | Prompt Injection and Jailbreaking |
| The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions | Papers | Prompt Injection and Jailbreaking |
| POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization | Papers | Prompt Injection and Jailbreaking |
| Simple Prompt Injection Attacks Can Leak Personal Data Observed by LLM Agents During Task Execution | Papers | Prompt Injection and Jailbreaking |
| "Give a Positive Review Only" - In-Paper Prompt Injection Attacks and Defenses for AI Reviewers | Papers | Prompt Injection and Jailbreaking |
| A Call to Action for a Secure-by-Design Generative AI Paradigm | Papers | Prompt Injection and Jailbreaking |
| A Multi-Agent LLM Defense Pipeline Against Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| A Simple and Efficient Jailbreak Method Exploiting LLMs' Helpfulness | Papers | Prompt Injection and Jailbreaking |
| A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search | Papers | Prompt Injection and Jailbreaking |
| AdaSteer: Your Aligned LLM is Inherently an Adaptive Jailbreak Defender | Papers | Prompt Injection and Jailbreaking |
| AI Agents May Always Fall for Prompt Injections | Papers | Prompt Injection and Jailbreaking |
| ASTRA: An Automated Framework for Strategy Discovery, Retrieval, and Evolution for Jailbreaking LLMs | Papers | Prompt Injection and Jailbreaking |
| Beyond Fixed and Dynamic Prompts: Embedded Jailbreak Templates for Advancing LLM Security | Papers | Prompt Injection and Jailbreaking |
| Bidirectional Intention Inference Enhances LLMs' Defense Against Multi-Turn Jailbreak Attacks | Papers | Prompt Injection and Jailbreaking |
| BreakFun: Jailbreaking LLMs via Schema Exploitation | Papers | Prompt Injection and Jailbreaking |
| BrowseSafe: Understanding and Preventing Prompt Injection Within AI Browser Agents | Papers | Prompt Injection and Jailbreaking |
| Can AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation | Papers | Prompt Injection and Jailbreaking |
| Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs | Papers | Prompt Injection and Jailbreaking |
| CourtGuard: A Local, Multiagent Prompt Injection Classifier | Papers | Prompt Injection and Jailbreaking |
| Dagger Behind Smile: Fool LLMs with a Happy Ending Story | Papers | Prompt Injection and Jailbreaking |
| Defending Against Prompt Injection with DataFilter | Papers | Prompt Injection and Jailbreaking |
| Enhancing Jailbreak Attacks on LLMs via Persona Prompts | Papers | Prompt Injection and Jailbreaking |
| Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs | Papers | Prompt Injection and Jailbreaking |
| ForgeDAN: An Evolutionary Framework for Jailbreaking Aligned Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning | Papers | Prompt Injection and Jailbreaking |
| HauntAttack: When Attack Follows Reasoning as a Shadow | Papers | Prompt Injection and Jailbreaking |
| In-Context Representation Hijacking | Papers | Prompt Injection and Jailbreaking |
| Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks? | Papers | Prompt Injection and Jailbreaking |
| Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models | Papers | Prompt Injection and Jailbreaking |
| LLM Jailbreak Detection for Almost Free | Papers | Prompt Injection and Jailbreaking |
| LLM Reinforcement in Context | Papers | Prompt Injection and Jailbreaking |
| May I have your Attention? Breaking Fine-Tuning based Prompt Injection Defenses using Architecture-Aware Attacks | Papers | Prompt Injection and Jailbreaking |
| Mitigating Indirect Prompt Injection via Instruction-Following Intent Analysis | Papers | Prompt Injection and Jailbreaking |
| NonTextual Target Attack - gradient-based untargeted jailbreak attack on LLMs | Papers | Prompt Injection and Jailbreaking |
| One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs | Papers | Prompt Injection and Jailbreaking |
| PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization | Papers | Prompt Injection and Jailbreaking |
| PIShield: Detecting Prompt Injection Attacks via Intrinsic LLM Features | Papers | Prompt Injection and Jailbreaking |
| Preventing Prompt Injection with Type-Directed Privilege Separation | Papers | Prompt Injection and Jailbreaking |
| Privacy-Preserving Prompt Injection Detection for LLMs Using Federated Learning and Embedding-Based NLP Classification | Papers | Prompt Injection and Jailbreaking |
| Prompt Fencing: A Cryptographic Approach to Establishing Security Boundaries in Large Language Model Prompts | Papers | Prompt Injection and Jailbreaking |
| Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Prompt injections as a tool for preserving identity in GAI image descriptions | Papers | Prompt Injection and Jailbreaking |
| PromptLocate: Localizing Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning | Papers | Prompt Injection and Jailbreaking |
| Retrieval-Augmented Defense: Adaptive and Controllable Jailbreak Prevention for Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Safeguarding Efficacy in LLMs: Evaluating Resistance to Human-Written and Algorithmic Adversarial Prompts | Papers | Prompt Injection and Jailbreaking |
| SAID: Safety-Aware Intent Defense via Prefix Probing for Large Language Models | Papers | Prompt Injection and Jailbreaking |
| Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments | Papers | Prompt Injection and Jailbreaking |
| SecInfer: Preventing Prompt Injection via Inference-time Scaling | Papers | Prompt Injection and Jailbreaking |
| Securing Large Language Models from Prompt Injection Attacks | Papers | Prompt Injection and Jailbreaking |
| Sugar-Coated Poison: Benign Generation Unlocks LLM Jailbreaking | Papers | Prompt Injection and Jailbreaking |
| System Prompt Poisoning: Persistent Attacks on Large Language Models Beyond User Injection | Papers | Prompt Injection and Jailbreaking |
| The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems | Papers | Prompt Injection and Jailbreaking |
| The Shawshank Redemption of Embodied AI: Understanding and Benchmarking Indirect Environmental Jailbreaks | Papers | Prompt Injection and Jailbreaking |
| What Features in Prompts Jailbreak LLMs? Investigating the Mechanisms Behind Attacks | Papers | Prompt Injection and Jailbreaking |
| Your AI, My Shell: Demystifying Prompt Injection Attacks on Agentic AI Coding Editors | Papers | Prompt Injection and Jailbreaking |
| Agentic JWT: A Secure Delegation Protocol for Autonomous AI Agents | Papers | Agent Security |
| Towards Trustworthy Agentic IoEV: AI Agents for Explainable Cyberthreat Mitigation and State Analytics | Papers | Agent Security |
| Exploit Tool Invocation Prompt for Tool Behavior Hijacking in LLM-Based Agentic System | Papers | Agent Security |
| Multi-Agent Systems Execute Arbitrary Malicious Code | Papers | Agent Security |
| Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations | Papers | Agent Security |
| ACE: A Security Architecture for LLM-Integrated App Systems | Papers | Agent Security |
| AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection | Papers | Agent Security |
| AgentVigil: Generic Black-Box Red-teaming for Indirect Prompt Injection against LLM Agents | Papers | Agent Security |
| A Whole New World: Creating a Parallel-Poisoned Web Only AI-Agents Can See | Papers | Agent Security |
| Web Fraud Attacks Against LLM-Driven Multi-Agent Systems | Papers | Agent Security |
| Throttling Web Agents Using Reasoning Gates | Papers | Agent Security |
| Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills | Papers | Agent Security |
| When AIOps Become "AI Oops": Subverting LLM-driven IT Operations via Telemetry Manipulation | Papers | Agent Security |
| MCPTox: A Benchmark for Tool Poisoning Attack on Real-World MCP Servers | Papers | Agent Security |
| Fortifying the Agentic Web: A Unified Zero-Trust Architecture Against Logic-layer Threats | Papers | Agent Security |
| Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems | Papers | Agent Security |
| DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agents | Papers | Agent Security |
| Context manipulation attacks: Web agents are susceptible to corrupted memory | Papers | Agent Security |
| AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models | Papers | Agent Security |
| LLM Agents Should Employ Security Principles | Papers | Agent Security |
| Securing AI Agents with Information-Flow Control | Papers | Agent Security |
| Adaptation of Agentic AI | Papers | Agent Security |
| Redefining Website Fingerprinting Attacks With Multiagent LLMs | Papers | Agent Security |
| Personalized Attacks of Social Engineering in Multi-turn Conversations: LLM Agents for Simulation and Detection | Papers | Agent Security |
| VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents | Papers | Agent Security |
| A Safety and Security Framework for Real-World Agentic Systems | Papers | Agent Security |
| A Vision for Access Control in LLM-based Agent Systems | Papers | Agent Security |
| A2AS: Agentic AI Runtime Security and Self-Defense | Papers | Agent Security |
| AAGATE: A NIST AI RMF-Aligned Governance Platform for Agentic AI | Papers | Agent Security |
| AI Kill Switch for Malicious Web-Based LLM Agents | Papers | Agent Security |
| BashArena: A Control Setting for Highly Privileged AI Agents | Papers | Agent Security |
| Breaking Agent Backbones - Evaluating the Security of Backbone LLMs in AI Agents | Papers | Agent Security |
| DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents | Papers | Agent Security |
| Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System | Papers | Agent Security |
| Formalizing the Safety, Security, and Functional Properties of Agentic AI Systems | Papers | Agent Security |
| Intelligent AI Delegation | Papers | Agent Security |
| Investigating the Impact of Dark Patterns on LLM-Based Web Agents | Papers | Agent Security |
| MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS | Papers | Agent Security |
| Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels | Papers | Agent Security |
| Mind the Web: The Security of Web Use Agents | Papers | Agent Security |
| Mind Viruses: Self-Propagating Ideas in Multi-Agent LLM Systems | Papers | Agent Security |
| MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents | Papers | Agent Security |
| Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks | Papers | Agent Security |
| Please Don't Kill My Vibe: Empowering Agents with Data Flow Control | Papers | Agent Security |
| SafeSearch: Automated Red-Teaming of LLM-Based Search Agents | Papers | Agent Security |
| SentinelNet: Safeguarding Multi-Agent Collaboration Through Credit-Based Dynamic Threat Detection | Papers | Agent Security |
| STAC: When Innocent Tools Form Dangerous Chains for LLM Agents | Papers | Agent Security |
| Systems Security Foundations for Agentic Computing | Papers | Agent Security |
| Takedown: How It's Done in Modern Coding Agent Exploits | Papers | Agent Security |
| The Dark Side of LLMs: Agent-based Attacks for Complete Computer Takeover | Papers | Agent Security |
| Trusted AI Agents in the Cloud | Papers | Agent Security |
| Uncovering Security Threats and Architecting Defenses in Autonomous Agents: A Case Study of OpenClaw | Papers | Agent Security |
| Whispering Agents: An event-driven covert communication protocol for the Internet of Agents | Papers | Agent Security |
| Who Grants the Agent Power? Defending Against Instruction Injection via Task-Centric Access Control | Papers | Agent Security |
| Your Agent Is Mine: Measuring Malicious Intermediary Attacks on the LLM Supply Chain | Papers | Agent Security |
| xOffense: An AI-driven autonomous penetration testing framework with offensive knowledge-enhanced LLMs and multi agent systems | Papers | Offensive Security and Red Teaming |
| From Firewalls to Frontiers: AI Red-Teaming is a Domain-Specific Evolution of Cyber Red-Teaming | Papers | Offensive Security and Red Teaming |
| Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks | Papers | Offensive Security and Red Teaming |
| Guided Reasoning in LLM-Driven Penetration Testing Using Structured Attack Trees | Papers | Offensive Security and Red Teaming |
| Automated Red Teaming with GOAT: the Generative Offensive Agent Tester | Papers | Offensive Security and Red Teaming |
| LLM Agents can Autonomously Hack Websites | Papers | Offensive Security and Red Teaming |
| Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments | Papers | Offensive Security and Red Teaming |
| Generative Artificial Intelligence-Supported Pentesting: A Comparison between Claude Opus, GPT-4, and Copilot | Papers | Offensive Security and Red Teaming |
| PentestAgent: Incorporating LLM Agents to Automated Penetration Testing | Papers | Offensive Security and Red Teaming |
| From Promise to Peril: Rethinking Cybersecurity Red and Blue Teaming in the Age of LLMs | Papers | Offensive Security and Red Teaming |
| Effective Red-Teaming of Policy-Adherent Agents | Papers | Offensive Security and Red Teaming |
| Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling | Papers | Offensive Security and Red Teaming |
| InjectLab: A Tactical Framework for Adversarial Threat Modeling Against Large Language Models | Papers | Offensive Security and Red Teaming |
| GenAI Security: Outsmarting the Bots with a Proactive Testing Framework | Papers | Offensive Security and Red Teaming |
| From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs | Papers | Offensive Security and Red Teaming |
| OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities | Papers | Offensive Security and Red Teaming |
| Cybersecurity AI: The World's Top AI Agent for Security Capture-the-Flag (CTF) | Papers | Offensive Security and Red Teaming |
| GPT-5 at CTFs: Case Studies From Top-Tier Cybersecurity Events | Papers | Offensive Security and Red Teaming |
| Accelerating AI Development with Cyber Arenas | Papers | Offensive Security and Red Teaming |
| PrompTrend: Continuous Community-Driven Vulnerability Discovery and Assessment for Large Language Models | Papers | Offensive Security and Red Teaming |
| A Comprehensive Evaluation and Practice of System Penetration Testing | Papers | Offensive Security and Red Teaming |
| Ask What Your Country Can Do For You: Towards a Public Red Teaming Model | Papers | Offensive Security and Red Teaming |
| ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System | Papers | Offensive Security and Red Teaming |
| Automated Vulnerability Validation and Verification: A Large Language Model Approach | Papers | Offensive Security and Red Teaming |
| Baselines Before Architecture: Evaluating Coding Agents for Autonomous Penetration Testing | Papers | Offensive Security and Red Teaming |
| Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing | Papers | Offensive Security and Red Teaming |
| Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs | Papers | Offensive Security and Red Teaming |
| Cybersecurity AI: Humanoid Robots as Attack Vectors | Papers | Offensive Security and Red Teaming |
| Dynamic Risk Assessments for Offensive Cybersecurity Agents | Papers | Offensive Security and Red Teaming |
| Exploiting AI for Attacks: On the Interplay between Adversarial AI and Offensive AI | Papers | Offensive Security and Red Teaming |
| From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization | Papers | Offensive Security and Red Teaming |
| LAPRAD: LLM-Assisted Protocol Attack Discovery | Papers | Offensive Security and Red Teaming |
| LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet? | Papers | Offensive Security and Red Teaming |
| LSPFuzz: Hunting Bugs in Language Servers | Papers | Offensive Security and Red Teaming |
| Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios | Papers | Offensive Security and Red Teaming |
| Measuring LLMs' impact on N-day exploits - Anthropic Frontier Red Team | Papers | Offensive Security and Red Teaming |
| MoPE: A Mixture of Password Experts for Improving Password Guessing | Papers | Offensive Security and Red Teaming |
| PoCGen: Generating Proof-of-Concept Exploits for Vulnerabilities in Npm Packages | Papers | Offensive Security and Red Teaming |
| Red Teaming AI Red Teaming | Papers | Offensive Security and Red Teaming |
| Red Teaming Large Reasoning Models | Papers | Offensive Security and Red Teaming |
| Risk Psychology and Cyber-Attack Tactics | Papers | Offensive Security and Red Teaming |
| Sensemaking in Security Assessment: An Interview Study of Expert Decision Making | Papers | Offensive Security and Red Teaming |
| Talking to the Airgap: Exploiting Radio-Less Embedded Devices as Radio Receivers | Papers | Offensive Security and Red Teaming |
| When Intelligence Fails: An Empirical Study on Why LLMs Struggle with Password Cracking | Papers | Offensive Security and Red Teaming |
| Evaluating and Improving the Robustness of Security Attack Detectors Generated by LLMs | Papers | Defense and Detection |
| Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks | Papers | Defense and Detection |
| AegisShield: Democratizing Cyber Threat Modeling with Generative AI | Papers | Defense and Detection |
| Can LLM Prompting Serve as a Proxy for Static Analysis in Vulnerability Detection | Papers | Defense and Detection |
| From Attack Descriptions to Vulnerabilities: A Sentence Transformer-Based Approach | Papers | Defense and Detection |
| Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs | Papers | Defense and Detection |
| IRCopilot: Automated Incident Response with Large Language Models | Papers | Defense and Detection |
| ThreatGPT: An Agentic AI Framework for Enhancing Public Safety through Threat Modeling | Papers | Defense and Detection |
| CyberRAG: An Agentic RAG cyber attack classification and reporting tool | Papers | Defense and Detection |
| SPEAR: Security Posture Evaluation using AI Planner-Reasoning on Attack-Connectivity Hypergraphs | Papers | Defense and Detection |
| SAVANT: Vulnerability Detection in Application Dependencies through Semantic-Guided Reachability Analysis | Papers | Defense and Detection |
| Artemis: Toward Accurate Detection of Server-Side Request Forgeries through LLM-Assisted Inter-Procedural Path-Sensitive Taint Analysis | Papers | Defense and Detection |
| What You Code Is What We Prove: Translating BLE App Logic into Formal Models with LLMs for Vulnerability Detection | Papers | Defense and Detection |
| A Systematic Approach to Predict the Impact of Cybersecurity Vulnerabilities Using LLMs | Papers | Defense and Detection |
| Trust Me, I Know This Function: Hijacking LLM Static Analysis using Bias | Papers | Defense and Detection |
| PromptKeeper: Safeguarding System Prompts for LLMs | Papers | Defense and Detection |
| System Prompt Extraction Attacks and Defenses in Large Language Models | Papers | Defense and Detection |
| Can AI Keep a Secret? Contextual Integrity Verification: A Provable Security Architecture for LLMs | Papers | Defense and Detection |
| Security Steerability is All You Need | Papers | Defense and Detection |
| Permissioned LLMs: Enforcing Access Control in Large Language Models | Papers | Defense and Detection |
| A Unified Framework for Human AI Collaboration in Security Operations Centers with Trusted Autonomy | Papers | Defense and Detection |
| Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences | Papers | Defense and Detection |
| Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks | Papers | Defense and Detection |
| Deep Think with Confidence | Papers | Defense and Detection |
| "Digital Camouflage": The LLVM Challenge in LLM-Based Malware Detection | Papers | Defense and Detection |
| A Comparative Evaluation of AI Agent Security Guardrails | Papers | Defense and Detection |
| A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks | Papers | Defense and Detection |
| Actionable Cybersecurity Notifications for Smart Homes: A User Study on the Role of Length and Complexity | Papers | Defense and Detection |
| AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software | Papers | Defense and Detection |
| AI-powered patching: the future of automated vulnerability fixes | Papers | Defense and Detection |
| AutoGuard: A Self-Healing Proactive Security Layer for DevSecOps Pipelines Using Reinforcement Learning | Papers | Defense and Detection |
| Automatically Generating Rules of Malicious Software Packages via Large Language Model | Papers | Defense and Detection |
| AVIATOR: Towards AI-Agentic Vulnerability Injection Workflow for High-Fidelity, Large-Scale Code Security Dataset | Papers | Defense and Detection |
| Bridging the Gap Between Security Metrics and Key Risk Indicators - An Empirical Framework for Vulnerability Prioritization | Papers | Defense and Detection |
| Cloud Security Leveraging AI: A Fusion-Based AISOC for Malware and Log Behaviour Detection | Papers | Defense and Detection |
| COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers | Papers | Defense and Detection |
| Cyberattack Detection in Critical Infrastructure and Supply Chains | Papers | Defense and Detection |
| Detecting Hard-Coded Credentials in Software Repositories via LLMs | Papers | Defense and Detection |
| Evaluating Large Language Models in detecting Secrets in Android Apps | Papers | Defense and Detection |
| Evaluating LLM Generated Detection Rules in Cybersecurity | Papers | Defense and Detection |
| Evaluating the Robustness of Large Language Model Safety Guardrails Against Adversarial Attacks | Papers | Defense and Detection |
| ExplainableGuard: Interpretable Adversarial Defense for LLMs Using Chain-of-Thought Reasoning | Papers | Defense and Detection |
| Heat-ray: Combating Identity Snowball Attacks Using Machine Learning, Combinatorial Optimization and Attack Graphs | Papers | Defense and Detection |
| Interpretable LLM Guardrails via Sparse Representation Steering | Papers | Defense and Detection |
| LLM-based Vulnerability Discovery through the Lens of Code Metrics | Papers | Defense and Detection |
| LLMs in the SOC: An Empirical Study of Human-AI Collaboration in Security Operations Centres | Papers | Defense and Detection |
| Prompt Engineering vs. Fine-Tuning for LLM-Based Vulnerability Detection in Solana and Algorand Smart Contracts | Papers | Defense and Detection |
| Prompting the Priorities: A First Look at Evaluating LLMs for Vulnerability Triage and Prioritization | Papers | Defense and Detection |
| QGuard: Question-based Zero-shot Guard for Multi-modal LLM Safety | Papers | Defense and Detection |
| RESCUE: Retrieval Augmented Secure Code Generation | Papers | Defense and Detection |
| Rescuing the Unpoisoned: Efficient Defense against Knowledge Corruption Attacks on RAG Systems | Papers | Defense and Detection |
| RulePilot: An LLM-Powered Agent for Security Rule Generation | Papers | Defense and Detection |
| Secure Retrieval-Augmented Generation against Poisoning Attacks | Papers | Defense and Detection |
| SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair | Papers | Defense and Detection |
| Security Logs to ATT&CK Insights: Leveraging LLMs for High-Level Threat Understanding and Cognitive Trait Inference | Papers | Defense and Detection |
| Towards Agentic Investigation of Security Alerts | Papers | Defense and Detection |
| VulSolver: Vulnerability Detection via LLM-Driven Constraint Solving | Papers | Defense and Detection |
| What Do They Fix? LLM-Aided Categorization of Security Patches for Critical Memory Bugs | Papers | Defense and Detection |
| You Can't Steal Nothing: Mitigating Prompt Leakages in LLMs via System Vectors | Papers | Defense and Detection |
| PII Jailbreaking in LLMs via Activation Steering Reveals Personal Information Leakage | Papers | Privacy and Data Security |
| Unveiling Privacy Risks in LLM Agent Memory | Papers | Privacy and Data Security |
| When GPT Spills the Tea: Comprehensive Assessment of Knowledge File Leakage in GPTs | Papers | Privacy and Data Security |
| Hush! Protecting Secrets During Model Training: An Indistinguishability Approach | Papers | Privacy and Data Security |
| Dataset Ownership in the Era of Large Language Models | Papers | Privacy and Data Security |
| Information Inference Diagrams: Complementing Privacy and Security Analyses Beyond Data Flows | Papers | Privacy and Data Security |
| Large-scale online deanonymization with LLMs | Papers | Privacy and Data Security |
| Prompt Pirates Need a Map: Stealing Seeds helps Stealing Prompts | Papers | Privacy and Data Security |
| An Efficient Gradient-Based Inference Attack for Federated Learning | Papers | Privacy and Data Security |
| Black Box Absorption: LLMs Undermining Innovative Ideas | Papers | Privacy and Data Security |
| Can LLMs Make Personalized Access Control Decisions? | Papers | Privacy and Data Security |
| Can You Trust Your Copilot? A Privacy Scorecard for AI Coding Assistants | Papers | Privacy and Data Security |
| How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code | Papers | Privacy and Data Security |
| Inference Attacks on Encrypted Online Voting via Traffic Analysis | Papers | Privacy and Data Security |
| Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models | Papers | Privacy and Data Security |
| Not My Agent, Not My Boundary? Elicitation of Personal Privacy Boundaries in AI-Delegated Information Sharing | Papers | Privacy and Data Security |
| Outlier and collapse: The Enron corpus and foundation model training data | Papers | Privacy and Data Security |
| Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems through Benign Queries | Papers | Privacy and Data Security |
| Toward provably private analytics and insights into GenAI use | Papers | Privacy and Data Security |
| What if we could hot swap our Biometrics? | Papers | Privacy and Data Security |
| When Speculation Spills Secrets: Side Channels via Speculative Decoding in LLMs | Papers | Privacy and Data Security |
| Who's Wearing? Ear Canal Biometric Key Extraction for User Authentication on Wireless Earbuds | Papers | Privacy and Data Security |
| Who Taught the Lie? Responsibility Attribution for Poisoned Knowledge in Retrieval-Augmented Generation | Papers | Model Security |
| Your Compiler is Backdooring Your Model: Understanding and Exploiting Compilation Inconsistency Vulnerabilities in Deep Learning Compilers | Papers | Model Security |
| Yet Another Watermark for Large Language Models | Papers | Model Security |
| The Coding Limits of Robust Watermarking for Generative Models | Papers | Model Security |
| Character-Level Perturbations Disrupt LLM Watermarks | Papers | Model Security |
| Factuality Beyond Coherence: Evaluating LLM Watermarking Methods for Medical Texts | Papers | Model Security |
| Reasoning Introduces New Poisoning Attacks Yet Makes Them More Complicated | Papers | Model Security |
| Poisoned at Scale: A Scalable Audit Uncovers Hidden Scam Endpoints in Production LLMs | Papers | Model Security |
| Backdoor Attacks and Defenses in Computer Vision Domain: A Survey | Papers | Model Security |
| A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives | Papers | Model Security |
| Adversarial Inception Backdoor Attacks against Reinforcement Learning | Papers | Model Security |
| Data Poisoning for In-context Learning | Papers | Model Security |
| Which Factors Make Code LLMs More Vulnerable to Backdoor Attacks? A Systematic Study | Papers | Model Security |
| MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models | Papers | Model Security |
| Adversarial Threat Vectors and Risk Mitigation for Retrieval-Augmented Generation Systems | Papers | Model Security |
| Trojans in Artificial Intelligence (TrojAI) Final Report | Papers | Model Security |
| RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering | Papers | Model Security |
| AttackPilot: Autonomous Inference Attacks Against ML Services With LLM-Based Agents | Papers | Model Security |
| BadThink: Triggered Overthinking Attacks on Chain-of-Thought Reasoning in Large Language Models | Papers | Model Security |
| Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment | Papers | Model Security |
| Do Not Merge My Model! Safeguarding Open-Source LLMs Against Unauthorized Model Merging | Papers | Model Security |
| EmoRAG: Evaluating RAG Robustness to Symbolic Perturbations | Papers | Model Security |
| Fingerprinting LLMs via Prompt Injection | Papers | Model Security |
| LLMs Cannot Reliably Judge Yet? A Comprehensive Assessment on the Robustness of LLM-as-a-Judge | Papers | Model Security |
| Modal Aphasia: Can Unified Multimodal Models Describe Images From Memory? | Papers | Model Security |
| Model Provenance Testing for Large Language Models | Papers | Model Security |
| On The Dangers of Poisoned LLMs In Security Automation | Papers | Model Security |
| On the Trade-Off Between Transparency and Security in Adversarial Machine Learning | Papers | Model Security |
| Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption | Papers | Model Security |
| Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering | Papers | Model Security |
| SBFA: Single Sneaky Bit Flip Attack to Break Large Language Models | Papers | Model Security |
| Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach | Papers | Model Security |
| Visual CoT Makes VLMs Smarter but More Fragile | Papers | Model Security |
| Zero-Knowledge Proof Based Verifiable Inference of Models | Papers | Model Security |
| AQUA-LLM: Evaluating Accuracy, Quantization, and Adversarial Robustness Trade-offs in LLMs for Cybersecurity Question Answering | Papers | General AI Security |
| GuardianPWA: Enhancing Security Throughout the Progressive Web App Installation Lifecycle | Papers | General AI Security |
| Demystifying Progressive Web Application Permission Systems | Papers | General AI Security |
| Secure Human Oversight of AI: Exploring the Attack Surface of Human Oversight | Papers | General AI Security |
| LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems | Papers | General AI Security |
| The Signalgate Case is Waiving a Red Flag to All Organizational and Behavioral Cybersecurity Leaders, Practitioners, and Researchers | Papers | General AI Security |
| Measuring the Vulnerability Disclosure Policies of AI Vendors | Papers | General AI Security |
| LLMs in Cybersecurity: Friend or Foe in the Human Decision Loop? | Papers | General AI Security |
| Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities | Papers | General AI Security |
| Six Million (Suspected) Fake Stars in GitHub: A Growing Spiral of Popularity Contests, Spams, and Malware | Papers | General AI Security |
| The Information Security Awareness of Large Language Models | Papers | General AI Security |
| ORCA: Unveiling Obscure Containers In The Wild | Papers | General AI Security |
| I Know Who Clones Your Code: Interpretable Smart Contract Similarity Detection | Papers | General AI Security |
| Establishing a Baseline of Software Supply Chain Security Task Adoption by Software Organizations | Papers | General AI Security |
| Adversarial Attacks Against Automated Fact-Checking: A Survey | Papers | General AI Security |
| Scamming the Scammers: Using ChatGPT to Reply Mails for Wasting Time | Papers | General AI Security |
| Generative AI in Cybersecurity | Papers | General AI Security |
| Hallucination is Inevitable: An Innate Limitation of Large Language Models | Papers | General AI Security |
| The Curse of Recursion: Training on Generated Data Makes Models Forget | Papers | General AI Security |
| Are Emergent Abilities of Large Language Models a Mirage? | Papers | General AI Security |
| Artificial Intelligence in the Knowledge Economy | Papers | General AI Security |
| Developing a Risk Identification Framework for Foundation Model Uses | Papers | General AI Security |
| Docker under Siege: Securing Containers in the Modern Era | Papers | General AI Security |
| A Review of Various Datasets for Machine Learning Algorithm-Based Intrusion Detection System: Advances and Challenges | Papers | General AI Security |
| Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things | Papers | General AI Security |
| A Human Study of Cognitive Biases in Web Application Security | Papers | General AI Security |
| Speed at the Cost of Quality: How Cursor AI Increases Short-Term Velocity and Long-Term Complexity in Open-Source Projects | Papers | General AI Security |
| The wall confronting large language models | Papers | General AI Security |
| Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity | Papers | General AI Security |
| Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media | Papers | General AI Security |
| Strategic Wealth Accumulation Under Transformative AI Expectations | Papers | General AI Security |
| Foundations of Large Language Models | Papers | General AI Security |
| REFRAG: Rethinking RAG based Decoding | Papers | General AI Security |
| Adapting Large Language Models to Emerging Cybersecurity using Retrieval Augmented Generation | Papers | General AI Security |
| AgentCyTE: Leveraging Agentic AI to Generate Cybersecurity Training and Experimentation Scenarios | Papers | General AI Security |
| AI Bill of Materials and Beyond: Systematizing Security Assurance through the AI Risk Scanning Framework | Papers | General AI Security |
| Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs | Papers | General AI Security |
| BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers | Papers | General AI Security |
| Beyond Model Jailbreak: Systematic Dissection of the "Ten Deadly Sins" in Embodied Intelligence | Papers | General AI Security |
| Characterizing Agentic Flooding of Government Services | Papers | General AI Security |
| DarkGram: A Large-Scale Analysis of Cybercriminal Activity Channels on Telegram | Papers | General AI Security |
| Drones that Think on their Feet: Sudden Landing Decisions with Embodied AI | Papers | General AI Security |
| ElectionSim: Massive Population Election Simulation Powered by Large Language Model Driven Agents | Papers | General AI Security |
| Fine-tuning of Large Language Models for Domain-Specific Cybersecurity Knowledge | Papers | General AI Security |
| From Description to Score: Can LLMs Quantify Vulnerabilities? | Papers | General AI Security |
| Frontier AI's Impact on the Cybersecurity Landscape | Papers | General AI Security |
| Hey GPT-OSS, Looks Like You Got It - Reasoning LLM Chain of Thought for Digital Forensics | Papers | General AI Security |
| High-Performance Dual-Node AI Infrastructure for Astrophysics and Cybersecurity | Papers | General AI Security |
| Hyperagents - self-referential, open-endedly self-improving AI agents | Papers | General AI Security |
| Investigating Security Implications of Automatically Generated Code on the Software Supply Chain | Papers | General AI Security |
| Large Language Model based Smart Contract Auditing with LLMBugScanner | Papers | General AI Security |
| Large Language Models as General Pattern Machines | Papers | General AI Security |
| Learned, Lagged, LLM-splained: LLM Responses to End User Security Questions | Papers | General AI Security |
| LLMs + Security = Trouble | Papers | General AI Security |
| LLMs can hide text in other text of the same length | Papers | General AI Security |
| Ocassionally Secure: A Comparative Analysis of Code Generation Assistants | Papers | General AI Security |
| Pliny on Lingua Ex Machina - procedural alien languages as covert channels in frontier AI | Papers | General AI Security |
| SecureBERT 2.0: Advanced Language Model for Cybersecurity Intelligence | Papers | General AI Security |
| Securing Large Language Models: Addressing Bias, Misinformation, and Prompt Attacks | Papers | General AI Security |
| Security Vulnerabilities in AI-Generated Code: A Large-Scale Analysis of Public GitHub Repositories | Papers | General AI Security |
| Security Vulnerabilities in Software Supply Chain for Autonomous Vehicles | Papers | General AI Security |
| Security Weaknesses of Copilot-Generated Code in GitHub Projects: An Empirical Study | Papers | General AI Security |
| Simulating Influence Dynamics with LLM Agents | Papers | General AI Security |
| STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation | Papers | General AI Security |
| Supporting Students in Navigating LLM-Generated Insecure Code | Papers | General AI Security |
| Toward Cybersecurity-Expert Small Language Models | Papers | General AI Security |
| Uncovering Vulnerabilities of LLM-Assisted Cyber Threat Intelligence | Papers | General AI Security |
| Using LLMs for Security Advisory Investigations: How Far Are We? | Papers | General AI Security |
| When AI Takes the Wheel: Security Analysis of Framework-Constrained Program Generation | Papers | General AI Security |
| When Code Crosses Borders: A Security-Centric Study of LLM-based Code Translation | Papers | General AI Security |
| Large Language Models for Security Operations Centers: A Comprehensive Survey | Papers | Surveys |
| Security Concerns for Large Language Models: A Survey | Papers | Surveys |
| Generative AI Security: Challenges and Countermeasures | Papers | Surveys |
| Safety at Scale: A Comprehensive Survey of Large Model Safety | Papers | Surveys |
| Primus: A Pioneering Collection of Open-Source Datasets for Cybersecurity LLM Training | Papers | Surveys |
| Organizational Adaptation to Generative AI in Cybersecurity: A Systematic Review | Papers | Surveys |
| From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem | Papers | Surveys |
| SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering? | Papers | Surveys |
| SafeGenBench: A Benchmark Framework for Security Vulnerability Detection in LLM-Generated Code | Papers | Surveys |
| A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures | Papers | Surveys |
| A Survey of Operating System Kernel Fuzzing | Papers | Surveys |
| CodeLLMPaper / ASE - curated literature database of agentic software engineering papers | Papers | Surveys |
| Exploring AI in Steganography and Steganalysis: Trends, Clusters, and Sustainable Development Potential | Papers | Surveys |
| Large Language Models for Cyber Security: A Systematic Literature Review | Papers | Surveys |
| SoK: Large Language Model Copyright Auditing via Fingerprinting | Papers | Surveys |
| SoK: Potentials and Challenges of Large Language Models for Reverse Engineering | Papers | Surveys |
| Structuring Security: A Survey of Cybersecurity Ontologies, Semantic Log Processing, and LLMs Application | Papers | Surveys |
| The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies | Papers | Surveys |
| The Evolution of Agentic AI in Cybersecurity: From Single LLM Reasoners to Multi-Agent Systems and Autonomous Pipelines | Papers | Surveys |
| The Prompt Report: A Systematic Survey of Prompt Engineering Techniques | Papers | Surveys |
| Unique Security and Privacy Threats of Large Language Models: A Comprehensive Survey | Papers | Surveys |
| Web Technologies Security in the AI Era: A Survey of CDN-Enhanced Defenses | Papers | Surveys |
| Lessons from Red Teaming 100 Generative AI Products - Microsoft AI Red Team whitepaper | Red Teaming | Resources |
| Mid-Year 2026 AI Model Security Research Report - XBOW | Red Teaming | Resources |
| State of AI in Business 2025 Report | General Reading | AI Industry and Ecosystem |
| Generative AI and the Nature of Work - SSRN | General Reading | AI Industry and Ecosystem |
| Robots and Labor in Nursing Homes | General Reading | AI Industry and Ecosystem |
| Signs of undeclared ChatGPT use in papers mounting | General Reading | AI Industry and Ecosystem |
| The 2025 AI Engineering Reading List | General Reading | AI Engineering |
| Papers with Code - The latest in Machine Learning | General Reading | Tutorials and Learning |
| Ilya 30u30 - Ilya Sutskever's 30 foundational deep learning papers reading list | General Reading | Tutorials and Learning |
| Compression, Correction, Confidentiality, and Comprehension: A Modern Look at Telegraph Codebooks | General Reading | Security News and Research |
| Understanding Windows Shellcode | General Reading | Security News and Research |