Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 papers Another 233 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 FAB 攻击，向声学基础模型植入可由环境声触发的后门
Published Oct 7
Evaluated models HuBERT-base , WavLM-base Abstract 论文提出了针对声学基模的 FAB 后门攻击，在弱威胁模型下实现了任务无关、物理可触发的后门植入。
提出 AdvSim2Real，协同训练网页智能体抵御页面注入
Published Oct 7
Evaluated models Qwen3.5-4B 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。
提出 Fed-ADR，用编排服务器协同操纵梯度攻破联邦学习并检测恢复
Published Sep 23
Evaluated models CNN（MNIST：2 Conv + 3 FC） , CNN（Fashion-MNIST：6 Conv + 1 FC） , ResNet18（CIFAR-10） Abstract Fed-ADR 用 gray-box 编排攻击绕过多种聚合防御，再用 Hessian 一致性检测和窗口内恢复把准确率拉回。Fed-ADR 是一套面向联邦学习的攻击、检测与恢复框架：编排服务器改写合谋客户端的梯度，使参数服务器的现有防御把投毒更新当成良性，同时在发现后用历史梯度把全局模型原地修回来。
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。
评测安全 Agent 在对抗性任务污染下的解题成功与开销
Published Sep 17
Evaluated models Gemma-4 31B , DeepSeek-V4 Flash , GPT-OSS 120B and others6 Abstract AgentLSD 用配对 web CTF 表明，欺骗性环境证据会改变安全智能体的解题率与工作量。AgentLSD 是一个对照框架，用来测量安全智能体在任务本身不变时，对对抗性任务污染的反应。
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 BPI 选点算法，增强去中心化联邦学习中的模型与数据投毒
Published Sep 2 Abstract BPI 用有限轮 gossip 暴露选拜占庭集合。作者把 DFL 中“破坏哪 m 个节点”写成攻击者在固定预算下的优化问题，并用 BPI 近似有限轮内诚实节点受到的拜占庭暴露。
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 提出针对 Agent 护栏的推理扩展拒绝服务攻击
Published Jun 12
Evaluated models TS-Guard-8B , Qwen3.5-9B , DeepSeek-V3.2 and others11 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。
Proposes DAERT, which uses simulated failures as reward to generate diverse adversarial instructions, exposing VLA language vulnerabilities.
Published Apr 7
Evaluated models π0 , OpenVLA , OpenVLA-7B and others5 Propose SABER, which uses a reinforcement learning attacker to rewrite instructions within a budget to cause VLA task failure.
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 red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.
You have reached the end