Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 265 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 SAFESHIELD，组织小语言模型部署时的安全决策
Published Oct 6
Evaluated models Qwen3-4B-Instruct Abstract SAFESHIELD 用可审计决策轨迹组织 SLM 部署时的四项安全决策，并报告协调依赖影响端到端结果。SAFESHIELD 是面向小语言模型的部署时安全框架，把运行时安全从单项审核改写成可检查的决策过程。
提出 APEXA，在工具层拒绝无执行支撑的结果并拦截电机命令
Published Sep 21
Evaluated models GPT-5-mini , GPT-5.4 , Claude Opus 4.7 and others4 Abstract 作者称执行是否发生要由工具层核对，而不能只靠提示词。APEXA 是先进光子源上的数据还原框架，用工具层代码约束语言模型智能体的工具调用。
提出 aiXamine 黑盒基准，统一评测 LLM 安全、稳健与隐私权衡
Published Aug 21
Evaluated models openai/gpt-5-mini , openai/gpt-4o , anthropic/claude-haiku-4.5 and others15 Abstract aiXamine 用九服务黑盒协议比较百余个模型，作者称单轴信任度进展可能削弱其他轴。aiXamine 是一套黑盒评测协议，用来在同一条件下比较 LLM 的 safety、security 与 privacy，而不是再产出一个能力分。
提出技能名称抢注攻击，利用 Agent 虚构技能名实施供应链劫持
Published Jul 14
Evaluated models GLM-4.5-Air , GPT-5.4-mini , Claude Sonnet 4.6 and others12 Abstract 研究证实智能体虚构技能名具有高发生率与可预测性，现有防御难以兼顾安全与效用，亟需注册表结构性防护。本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险，将其形式化为一种新型供应链抢注攻击。
提出谱系图治理层抑制多智能体协作的错误级联
Published Mar 4 Abstract 单一种子可沿固定协作图固化为错误共识。作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。
用 TEE-REDBENCH 评测 TEE 顾问的机制幻觉与提示诱导失败
Published Feb 23
Evaluated models ChatGPT-5.2 , Claude Opus-4.6 Abstract 作者用 TEE-REDBENCH 测两款顾问，称失败可迁移且流水线控制可降低发生率。TEE-REDBENCH 红队评测被当作 Intel SGX 与 Arm TrustZone 安全顾问的 ChatGPT-5.2 和 Claude Opus-4.6，看架构推理、远程证明语义、缓解建议和策略约束下的拒答，并测提示诱导失败能否跨助手迁移。作者把助手看成随机策略。
You have reached the end