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

#adversarial-prompts

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

Stories per day · 30 days

Relatedred-teaming2 ai-safety1 dtap-bench1 harmbench1 jailbreak1 llm-agents1 llm-security1 self-criticism1

2 stories, newest first · one card per story

arXiv cs.CR4d ago

Paper says target agents criticize attacks better than they propose them

Separating criticism and proposal reached 63.2% attack success on DTAP-BENCH across four domains.

red-teaming llm-agents

arXiv cs.CR16d ago

Diagnose Before You Refine: Multi-Dimensional Judge Feedback for Query-Efficient Jailbreak Attacks

A new paper reports a query-efficient jailbreak method with 89.8% HarmBench success in 10 queries.

jailbreak llm-security

2