arXiv (systems & security) cs.CROct 14, 2026Research
Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak AttacksGitHub #llmOct 11, 2026New Repos & Packages
onehumanbeing/esp32-iphone-agent (2,944 stars)arXiv (systems & security) cs.LGOct 7, 2026Research
PatchBench: Measuring Collateral Damage in Activation PatchingarXiv (systems & security) cs.CROct 1, 2026Research
MOMAT: Mixture of Multiple Atlases for Low-Power Jailbreak Defense of Quantized LLMsarXiv (systems & security) cs.CRSep 30, 2026Research
CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code CompletionarXiv (systems & security) cs.CRSep 30, 2026Research
SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMsarXiv cs.AISep 25, 2026Research
Monitor Jailbreaking: Evading Chain-of-Thought Monitoring Without Encoded ReasoningarXiv (systems & security) cs.MMSep 25, 2026Research
TempQ-Jail: Query-Constrained Candidate Ranking for Text-to-Video Jailbreak AttacksAnacondaSep 24, 2026News
Your AI Passed the Jailbreak Tests: Here’s What They MissedarXiv (systems & security) cs.SDSep 24, 2026Research
AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks