BrainwashedLLM automates RL-based Chain-of-Thought jailbreaks for LRMs
BrainwashedLLM automates discovery of reasoning-based jailbreaks that transfer zero-shot to larger LRMs.
Stories per day · 30 days
3 stories, newest first · one card per story
Stories tagged #adversarial-reasoning
Adversarial speculative decoding improves long-horizon agent reasoning
Training draft models to be rejected at critical points raises end-to-end success on complex agentic coding benchmarks without changing target model output.
Claude Mythos 5 is coming to Tenable One, powering the new “Adversary View”
Tenable will integrate Anthropic's Claude Mythos 5 into Tenable One, launching Adversary View to surface exploitable vulnerability chains from scan data.
3