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.
Derail yourself: Multi-turn llm jailbreak attack through self- discovered clues
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
baseline 1
citation-polarity summary
representative citing papers
SafeSteer restricts reverse KL penalty to safety tokens selected via activation steering, achieving strong safety on seven benchmarks with minimal degradation on five capability benchmarks using only 100 harmful samples and no general data.
TurnGate identifies the critical turn in multi-turn dialogues where a response would complete hidden malicious intent, outperforming baselines on the new MTID dataset while keeping over-refusal low.
TrajGuard detects jailbreaks by tracking how hidden-state trajectories move toward high-risk regions during decoding, achieving 95% defense rate with 5.2 ms/token latency across tested attacks.
EvoSynth evolves code-based jailbreak algorithms via multi-agent self-correction, reaching 85.5% ASR on Claude-Sonnet-4.5 and 95.9% average across targets with greater diversity.
AGILE is a two-stage jailbreak attack that combines scenario-based rephrasing with activation-guided local editing to reach state-of-the-art attack success rates and strong black-box transferability.
citing papers explorer
-
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
EvoSynth evolves code-based jailbreak algorithms via multi-agent self-correction, reaching 85.5% ASR on Claude-Sonnet-4.5 and 95.9% average across targets with greater diversity.