Empirical study of 400 LLM attack runs finds exploitation success rates of 25-85% across four models against a fixed multi-service honeypot, with model-distinctive failure modes and p<0.001 differences.
Hiding in the AI traffic: Abusing MCP for LLM -powered agentic red teaming
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
No major agentic AI framework complies with six safety containment principles; a memory poisoning attack on LangChain causes persistent targeted errors up to 88.9% wrongful denials and 3.5x increase under complex policies, fixed by two sub-millisecond validators.
citing papers explorer
-
How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency
Empirical study of 400 LLM attack runs finds exploitation success rates of 25-85% across four models against a fixed multi-service honeypot, with model-distinctive failure modes and p<0.001 differences.
-
The Containment Gap: How Deployed Agentic AI Frameworks Fail Public-Facing Safety Requirements
No major agentic AI framework complies with six safety containment principles; a memory poisoning attack on LangChain causes persistent targeted errors up to 88.9% wrongful denials and 3.5x increase under complex policies, fixed by two sub-millisecond validators.