Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 15 papers Another 218 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 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感
Published Oct 2
Evaluated models Gemma-3-27B-Instruct , Gemma-3-4B-Instruct , Llama-3.2-3B-Instruct and others12 提出能力洗钱攻击，拆分任务向对齐模型套取能力
Published Sep 14
Evaluated models GPT-5.5 , Claude Opus 4.8 , Grok-4.3 and others7 Abstract 作者提出了能力洗钱攻击，发现未对齐编排器分解咨询对齐模型可恢复能力差距，指出需建立跨会话防御。
提出 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御
Published Sep 9
Evaluated models CodeLlama-13B-Instruct , DeepSeekCoder-V2-Lite-16B , GPT-OSS-20B and others7 Abstract 论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。
提出 RedEvoAgent，演化攻击技能对黑盒智能体做自动红队
Published Aug 28
Evaluated models MiniMax-M2.5 , DeepSeek-V4-Flash , Qwen3.5-35B Abstract RedEvoAgent 用验证棘轮演化可读攻击技能，在两种产品级 harness 上多数设置高于固定工具与红队基线。RedEvoAgent 是面向产品级 black-box 智能体的自动红队方法，用一份可演化、人类可读的攻击技能编排多个越狱工具。 。
提出 ColluSkill，用跨技能组合绕过 Agent 技能扫描器
Published Aug 10
Evaluated models GPT-5.5 , DeepSeek-V4-Pro , GLM-5.2 Abstract 论文揭示了单技能孤立扫描的盲区，提出多技能链攻击 ColluSkill 与上下文防御 ChainGuard 并验证了有效性。
提出 SkillClone，仅凭良性任务交互重构闭源 Agent 技能
Published Aug 5
Evaluated models DeepSeek-Flash , DeepSeek-Pro , GLM-5.1 and others5 Abstract 论文揭示了仅靠良性任务交互即可重构闭源智能体技能隐藏功能的风险，表明功能保密需要限制累积信息泄露。论文从功能保密视角系统研究了大语言模型智能体技能的行为重构威胁。
训练自博弈红队智能体 GPT-Red，规模化生成提示注入与越狱攻击
Published Jul 29
Evaluated models GPT-5.6 , GPT-5.5 , GPT-5.4 and others8 提出 SigLeak，从黑盒 Agent 执行轨迹推断专有技能
Published Jul 28
Evaluated models GPT-5.4-mini , GPT-5.5 , GLM-5.2 and others4 Abstract 提出了通过良性查询和对照轨迹推断黑盒专有技能的 SigLeak 框架，揭示了智能体执行可见性带来的行为侧信道泄露风险。
提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念
Published Jul 13
Evaluated models Minimax-M2.7 , Kimi-K2.6 , Deepseek-V4-Pro and others5 Abstract 论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。
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 CoT Forgery，经用户消息或工具输出注入伪造推理
Published Feb 23
Evaluated models gpt-oss-20b , gpt-oss-120b , o4-mini and others11 Abstract 提示注入被作者解释为角色感知失败：听起来像某角色，就在表示里成为该角色。作者把提示注入解释成角色感知失败：标签划出的权限没有进入模型的内部几何。
提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型
Published Jan 9
Evaluated models DeepSeek-V3 , Qwen3-32B , GPT-OSS-120B Abstract iMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。iMIST 是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。
Attacks arXiv 2512.20168 · Dec 23, 2025 提出双重隐写越狱 Odysseus，用图像隐写绕过多模态系统安全过滤器
Published Dec 23, 2025
Evaluated models GPT-4o-2024-08-06 , Gemini-2.0-pro , Gemini-2.0-flash and others4 Attacks arXiv 2510.09023 · Oct 10, 2025 提出自适应攻击框架，击穿越狱与提示注入防御
Published Oct 10, 2025
Evaluated models Gemini-2.5 Pro , GPT-5 Mini , Llama-3.3 70B and others15 Attacks arXiv 2509.25624 · Sep 30, 2025 提出 STAC 框架，把恶意目标拆成多轮看似无害的工具调用链
Published Sep 30, 2025
Evaluated models GPT-4.1-2025-04-14 , GPT-4.1-mini-2025-04-14 , Qwen3-32B and others8 Abstract 作者提出并验证了智能体在序列化工具攻击下的普遍脆弱性，指出针对累积动作序列防御的必要性。
You have reached the end