# adaptive-attacks
標記為「adaptive-attacks」的 6 篇文章
The Attacker Moves Second Problem
Why static LLM defenses fail against adaptive adversaries: analysis of 12 bypassed defenses and implications for defense design.
Reasoning Model Jailbreaks
How reasoning capabilities create novel jailbreak surfaces: chain-of-thought exploitation, scratchpad attacks, and why higher reasoning effort increases attack success.
Adaptive Attacks Against Safety Training
Research on attacks that adapt to safety training procedures to discover persistent vulnerabilities.
The 攻擊er Moves Second Problem
Why static LLM defenses fail against adaptive adversaries: analysis of 12 bypassed defenses and implications for defense design.
Reasoning 模型 越獄s
How reasoning capabilities create novel jailbreak surfaces: chain-of-thought exploitation, scratchpad attacks, and why higher reasoning effort increases attack success.
Adaptive 攻擊s Against Safety 訓練
Research on attacks that adapt to safety training procedures to discover persistent vulnerabilities.