Detect-and-misdirect defenses bound asymptotic attacker success rates in model-guided jailbreaks on agentic AI, unlike detect-and-block which permit near-certain success with sufficient queries.
Jailbroken: How does LLM safety training fail? In Advances in Neural Information Processing Systems, vol- ume 36, pages 80079–80110, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
Detect-and-misdirect defenses bound asymptotic attacker success rates in model-guided jailbreaks on agentic AI, unlike detect-and-block which permit near-certain success with sufficient queries.