Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 305 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤
Published Oct 7
Evaluated models Qwen2.5-3B-Instruct , Qwen2.5-14B-Instruct , gemma-3-4b-it and others8 Abstract 论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。
提出 ENDOPROMPT，以受害者侧伪参考学习降低良性任务效用的前缀
Published Sep 24
Evaluated models Qwen2.5-7B , Llama-3.1-8B , Mistral-7B-v0.3 and others4 Abstract 作者用受害模型续写监督良性效用攻击，并把行为位移、任务退化与请求匹配效果分开评测。ENDOPROMPT 是一种用受害模型自身续写监督前缀生成的 white-box 效用攻击方法。 它针对良性任务失败，不要求产生有害内容或明确拒答。
测量记忆投毒防御在良性对话上的效用与 token 开销
Published Sep 19 Abstract 写时代价落在噪声内。在没有攻击的对话上，给记忆投毒防御计价，而不是再测一轮攻击是否被挡住。
提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现
Published Sep 14
Evaluated models TF-IDF + logistic regression , DistilBERT , DeBERTa-v3-FT and others7 Abstract PIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。
提出 RolePlay 框架，用人设条件放大 LLM 单次推理开销
Published Jul 29
Evaluated models DeepSeek-V4-Pro , Gemini-3.5-Flash , Qwen-3.5-Plus and others5 提出层级遗传算法 HGA，扰动题目逻辑结构诱发推理模型过度思考
Published May 13
Evaluated models DeepSeek-R1 (671B) , Qwen3-Thinking , GPT-o3 and others5 Abstract HGA 在黑盒推理模型上用逻辑扰动拉长输出，作者称可从小代理迁移，查询成本是其局限。
提出 DAERT，以仿真失败为奖励生成多样对抗指令，暴露 VLA 的语言脆弱性
Published Apr 7
Evaluated models π0 , OpenVLA , OpenVLA-7B and others5 提出 SABER，用强化学习攻击器在预算内改写指令使 VLA 任务失败
Published Mar 26
Evaluated models π0-LIBERO , π0.5 , X-VLA and others6 提出 Aegis 红队框架，多轮攻击高风险语音 Agent
Published Feb 7
Evaluated models GPT-4o , GPT-4o-mini , Gemini-1.5 Pro and others7 Abstract Aegis 红队评测三类语音智能体：查询式访问消掉认证与泄密成功，行为类攻击仍在。Aegis 用多轮红队评测已接入业务系统的 ALLM 语音智能体。作者称这是该设定下的 the first systematic red-teaming framework。
You have reached the end