Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
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 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 MIRROR，用多路径摘要多数表决保障多智能体通信完整性
Published Oct 2
Evaluated models Gemma-4-31B-it , Gemini 2.5 Pro Abstract MIRROR 靠多数路径。MIRROR 是 LLM 多智能体通信层上的多路径法定人数完整性原语，只处理不透明字节，不解释消息内容。要处理的是 Agent-in-the-Middle：中介合法终结 TLS 后可改在途消息，而语义校验有推理开销和误拦，签名又要求私钥管理。做法是生成结束后复制同一规范化载荷。
提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描
Published Sep 25
Evaluated models GPT-5.4 , GPT-5.4 Mini , Claude Opus 4.6 and others11 Abstract 论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。
提出两阶段框架 A2M，优化 MCP 工具元数据与返回载荷以劫持 Agent
Published Sep 23
Evaluated models GLM-4.6 , Qwen3-Max , DeepSeek-V3.1 and others5 提出 ISM，用语义匹配隐式操纵 Agent 技能选择
Published Sep 2
Evaluated models Llama-2-7B , Llama-3-8B , Llama-3.1-8B and others8 提出利用检查点回滚破坏 Agent 执行连续性的攻击
Published Aug 30 Abstract 论文系统研究了智能体 C/R 的安全性，分析了合法回滚破坏执行连续性的机理，并实证评估了其普遍性与危害。
为去中心化 LLM 推理网络提出稳健成本感知 PoQ，抵御恶意评估者操纵分数
Published Jan 29
Evaluated models llama 3 2 3b , gemma 2 2b it , tinyllama 1 1b and others10 Abstract 成本感知 PoQ 加入稳健共识。这篇扩展工作把成本感知 Proof of Quality 的共识层改成能承受恶意评估分数的形式，奖励仍同时看输出质量与延迟成本。
You have reached the end