Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 10 papers Another 215 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.
评测编码智能体 harness 安全机制在对抗任务中的防护效果
Published Oct 6 构建可组合工具包 pikit，评测编码智能体的间接提示注入
Published Sep 29 Abstract pikit 提供组合式间接注入评测。pikit 是面向间接提示注入研究的组合式工具包 ，主要贡献是组织攻击、投递通道、防御和判定流程，而非提出新的攻击优化算法。
提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作
Published Sep 26
Evaluated models Claude-Sonnet-5 , Claude-Opus-5 , GPT-5.6-Sol and others14 Abstract 论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。
诊断 BatchNorm 架构下机器遗忘评测的归一化伪影
Published Sep 8
Evaluated models ResNet-18 , ResNet-50 , ViT-S/16 and others4 Abstract 一次不改权重的 BN 重校准能翻转多数方法的表面遗忘，但不改变权重里的编码器泄露。BN illusion 是作者对近似机器遗忘评测中一种 BatchNorm 测量伪影的命名：不改权重、只用 retain 数据重算运行统计，就可以把表面遗忘准确率翻过来。
提出 SYNCHAIN，诱导计算机使用 Agent 自建跨任务持久攻击链
Published Aug 7
Evaluated models Qwen3.5-9B , Llama-3.1-8B , Ministral-3-8B Abstract 论文揭示了 CUA 自合成工件带来的内部供应链威胁，验证了潜伏载荷的跨任务传播能力与防御局限。
Proposes IssueTrojanBench to evaluate coding agents' execution of malicious issues
Published Jul 23
Evaluated models GPT-5.3 Codex , GPT-5.4 , Sonnet 4.6 评测编码 Agent 记忆文件中提示注入的跨会话影响
Published Jul 16
Evaluated models Claude Haiku 4.5 , Claude Opus 4.7 , GPT-5.2 and others4 Abstract 已植入记忆文件的载荷可以跨会话影响 Claude Code 与 Codex，攻击成功与载荷是否留下是两种不同的失败。Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。
用代价曲线评估恶意微调防御在持续训练下的衰减
Published May 14
Evaluated models Llama-2-7B-chat , Qwen3-8B , Llama-3.1-8B-Instruct and others8 Abstract 论文指出恶意微调防御在持续训练下均会衰减，表明基于有限攻击者假设的防御无法为开源模型提供持久保护。
提出 AgentHazard 基准，评测计算机使用智能体的执行层有害行为
Published Apr 3
Evaluated models Qwen2.5-72B-Instruct , Qwen2.5-Coder-32B-Instruct , Qwen3-32B and others12 Abstract AgentHazard 评估了计算机使用智能体的执行安全，作者认为模型层对齐无法可靠保障智能体层面的安全性。AgentHazard 是针对计算机使用智能体执行层安全构建的评估基准，重点探究多步工具调用下局部合理动作累积引发的危害。
提出 JAWS-Bench，评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性
Published Oct 2, 2025
Evaluated models GPT-4.1 , GPT-o1 , DeepSeek-R1 and others8 Abstract 论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench，发现多文件与智能体推理会明显放大可部署危害。
You have reached the end