Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 14 papers Another 240 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.
Proposing SWE-Critix, a post-trained general verifier for evaluating coding agent trajectories
Published Oct 9
Evaluated models Qwen3-30B-A3B-Thinking-2507 , SWE-Critix SFT , SWE-Critix RL 提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务
Published Oct 8
Evaluated models ObligationGuard , Claude-Opus-4.8 , GPT-5.6-Sol and others17 Abstract 义务是护栏缺口。作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。
提出 PyCache Trap，用字节码缓存替换绕过 Agent 技能扫描器
Published Oct 7
Evaluated models CISCO , HSS , AUDITOR and others8 Abstract 论文剖析智能体技能审查与执行脱节盲区，提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。这篇论文研究了智能体技能（Agent Skills）安全扫描中的“审查–执行脱节”问题，并提出了对应的攻击验证与防御方案。
提出 VERA，审计 LLM 漏洞解释里的虚构推理
Published Oct 5
Evaluated models sonnet-5 , gemma-4-26b , llama-4-maverick and others8 检验低监控读数能否证明代码生成中的奖励作弊已受控
Published Oct 2
Evaluated models Llama-3.1-8B-Instruct Abstract 论文指出监控器训练读数接近零无法确立作弊受控，模型可利用通用外壳推迟提交绕过监控，强化学习亟需带外行为验证。本文是一篇针对强化学习可验证奖励后训练（RLVR）中监控器有效性与奖励作弊行为的实证分析研究。论文要解决的核心问题是：在训练目标中引入监控器以抑制代码生成中的作弊行为时，接近零的监控器读数是否足以确立模型行为已真正受控。
构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效
Published Sep 30
Evaluated models Qwen3-4B , Qwen3.5-27B Abstract CATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。
提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改
Published Sep 29
Evaluated models Claude Code (claude -p, version 2.1) , 独立评审（同一 CLI，无工具） Abstract Tracekit 把意图、自述和动作写入可锚定的哈希链。Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。
提出 SkillDRE，用预执行与运行时双阶段反馈演化恶意 Agent 技能
Published Sep 26
Evaluated models DeepSeek-V4-Pro , GLM-5.2 , Qwen3.5-397B-A17B and others4 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。
提出隐蔽后门攻击 AKRASIA，在推理代码模型提示中植入触发器并伪装思维链
Published Sep 1
Evaluated models Claude-Sonnet-5 , GPT-5.5 , Gemini-3.5-flash and others7 Abstract 论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA，揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。
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。
Proposes a static-first validator, CARE, that decides before dispatch whether an agent's shell command may be executed
Published Jul 22 Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents
Published Mar 16
Evaluated models multi-modal-embed-small Abstract Perception errors can be exploited by swapping screen pixels.The authors frame CUA's perception failure as a security vulnerability, visual confused deputy : the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.
Attacks arXiv 2509.05372 · Sep 4, 2025 用对抗缺陷报告诱导自动程序修复系统生成不安全补丁
Published Sep 4, 2025
Evaluated models claude-sonnet-4-20250514 , o4-mini , GPT-4.1-mini and others8 You have reached the end