NewA calmer, faster ZeroHour — security assessments on articles, story timelines and search from any page.

#jailbreakbench

0 stories this week · 2 this month · 2 in 6 months · mostly AI

Stories per day · 30 days

Relatedgcg1 guardrails1 harmbench1 jailbreak1 llm-evaluation1 over-refusal1 pair1 safety-benchmarks1

2 stories, newest first · one card per story

arXiv cs.CR11d ago

Paper proposes ASR_STEP to discount iterative LLM jailbreaks

On JailBreakBench, discounting victim-model calls lowers GCG by 7.0 to 8.7 points and PAIR by 3.4 to 12.

jailbreak llm-evaluation

1

Hugging Face daily papers13d ago

Guardrail safety scores track policy labels more than detection capability

Ten arms trained on about 53k dual-labeled prompts show HarmBench-copyright scores spanning 0-100 while detection stays unchanged.

guardrails safety-benchmarks

1