attack defense

Defensive Misdirection Strategy Cuts Automated Attack Success on Agentic AI Systems by Two Orders of Magnitude

A new analysis from arXiv shows that conventional detect-and-block defenses against prompt-injection and jailbreak attacks on agentic AI systems can be defeated as query budgets grow. The authors propose a detect-and-misdirect strategy, with a proof-of-concept method called Contextual Misdirection via Progressive Engagement (CMPE) that reduces attacker success rate upper bounds by up to two orders of magnitude on standard benchmarks.