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

#advbench

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

Stories per day · 30 days

Relatedblack-box1 harmbench1 jailbreak1 llm-safety1

2 stories, newest first · one card per story

arXiv cs.CR26d ago

ECHO jailbreak search scores reply harmfulness instead of compliance prefixes

Authors report up to 0.898 StrongREJECT and 89.23% HarmBench success on five open-weight models; code is public.

jailbreak llm-safety

1

arXiv cs.CRSep 24, 2026

Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs

Output-prefix attacks plus injected reasoning jailbreak Gemini, DeepSeek, and Claude models at up to 99% success.

prompt-injection jailbreak

2