A multi-turn intention-deception jailbreak achieves high success on GPT-5 and Claude models while exposing para-jailbreaking where models leak harmful information without direct refusal.
Parden, can you repeat that? defending against jailbreaks via repetition
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
CoopGuard deploys cooperative agents to track conversation history and counter evolving multi-round attacks on LLMs, achieving a 78.9% reduction in attack success rate on a new 5,200-sample benchmark.
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.
citing papers explorer
-
Jailbreaking Frontier Foundation Models Through Intention Deception
A multi-turn intention-deception jailbreak achieves high success on GPT-5 and Claude models while exposing para-jailbreaking where models leak harmful information without direct refusal.
-
RACC: Representation-Aware Coverage Criteria for LLM Safety Testing
RACC defines six representation-aware coverage criteria that score jailbreak test suites by measuring activation of safety concepts extracted from LLM hidden states on a calibration set.
-
CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks
CoopGuard deploys cooperative agents to track conversation history and counter evolving multi-round attacks on LLMs, achieving a 78.9% reduction in attack success rate on a new 5,200-sample benchmark.
-
Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety
A comprehensive survey that taxonomizes safety threats to large models and agents, reviews defenses and benchmarks, and outlines open challenges.