Intel · itspricedin.lol

🕵️ Intel feed — 5660 resources from the ai-security compendium

Categories: Agent Frameworks · Agent Identity · Agent Security · Anti-Crawling · Architecture · Benchmarks · Code Analysis · Coding Tools · Detection and Monitoring · Engineering Patterns · Frameworks and Standards · General Reading · Governance and Policy · Guardrails and Firewalls · Honeypots and Deception · Incidents · Jailbreaking · MCP (Model Context Protocol) · Model Attacks · Papers · Privacy · Prompt Injection · Red Teaming · Safety and Alignment · Sandboxing and Isolation · Secrets Management · Secure Coding · Supply Chain · Threat Modeling

Showing 35 of 35. Source: github.com/AnthonyHerman/ai-security-corpus · browse it in Internet Explorer. This is the research; the markets are the bets.

Snapshot 2026-10-10 · last checked 2026-10-13 14:25 UTC · NEW = added in the last 14 days (nothing fresh this fortnight; the bugs are resting)

Title	Category	Section
Bias Injection Attacks on RAG Databases and Sanitization Defenses	Model Attacks	Data Poisoning
Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis	Model Attacks	Data Poisoning
Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors	Model Attacks	Data Poisoning
Layer of Truth: Probing Belief Shifts under Continual Pre-Training Poisoning	Model Attacks	Data Poisoning
Nightshade, the free tool that 'poisons' AI models, is now available for artists to use	Model Attacks	Data Poisoning
Stack Overflow for AI Agents Sounds Great Until Someone Poisons the Answers	Model Attacks	Data Poisoning
Virus Infection Attack on LLMs: Your Poisoning Can Spread VIA Synthetic Data	Model Attacks	Data Poisoning
AutoBackdoor: Automating Backdoor Attacks via LLM Agents	Model Attacks	Backdoors and Trojans
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning	Model Attacks	Backdoors and Trojans
CacheTrap: Injecting Trojans in LLMs without Leaving any Traces in Inputs or Weights	Model Attacks	Backdoors and Trojans
Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models	Model Attacks	Backdoors and Trojans
How to Backdoor Large Language Models - BadSeek	Model Attacks	Backdoors and Trojans
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain	Model Attacks	Backdoors and Trojans
Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation	Model Attacks	Backdoors and Trojans
Persistent Backdoor Attacks under Continual Fine-Tuning of LLMs	Model Attacks	Backdoors and Trojans
Rethinking Backdoor Detection Evaluation for Language Models	Model Attacks	Backdoors and Trojans
ShadowLogic: Backdoors in Any Whitebox LLM	Model Attacks	Backdoors and Trojans
ToxScreen: Detecting Whether an LLM Has Been Poisoned	Model Attacks	Backdoors and Trojans
Watch Out for the Lifespan: Evaluating Backdoor Attacks Against Federated Model Adaptation	Model Attacks	Backdoors and Trojans
Your Open Source Model Could Have a Hidden Time-Release Backdoor	Model Attacks	Backdoors and Trojans
A Systematic Study of Model Extraction Attacks on Graph Foundation Models	Model Attacks	Model Extraction and Stealing
delta-STEAL: LLM Stealing Attack with Local Differential Privacy	Model Attacks	Model Extraction and Stealing
Detecting and preventing distillation attacks	Model Attacks	Model Extraction and Stealing
HN comment on Chinese resellers offering Claude tokens 70-90% off and selling reasoning traces as training data	Model Attacks	Model Extraction and Stealing
Michael Kratsios: Moonshot AI covertly distilled Anthropic's Fable to build its K3 model	Model Attacks	Model Extraction and Stealing
Ox Alpha is GLM - reverse engineering a stealth OpenRouter model via prompt injection	Model Attacks	Model Extraction and Stealing
Stolen Thoughts - Stealing Reasoning Traces from Proprietary LLM APIs	Model Attacks	Model Extraction and Stealing
Beyond the Board: Exploring AI Robustness Through Go	Model Attacks	Adversarial Examples
Certified but Fooled! Breaking Certified Defences with Ghost Certificates	Model Attacks	Adversarial Examples
PReMA - adversarial image attack exploiting text-image misalignment in multi-modal diffusion models	Model Attacks	Adversarial Examples
Special-Character Adversarial Attacks on Open-Source Language Model	Model Attacks	Adversarial Examples
This adversarial pattern can prevent surveillance cameras from detecting you	Model Attacks	Adversarial Examples
StealthGPT - AI humanizer and undetectable AI writer	Model Attacks	Watermarking Attacks
watermarks-remover - strips AI watermarks from content you own	Model Attacks	Watermarking Attacks
A Framework for Rapidly Developing and Deploying Protection Against Large Language Model Attacks	Papers	Defense and Detection

🐧 guest@itspricedin: ~

📁 Markets

AddressC:\MARKETS\

9 folder(s). Single-click opens; it is 1995, nobody has time for double. Prices are probabilities, $POC is nothing.