Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 17 papers 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 CRIME 框架，组合良性 Agent 技能诱发恶意行为
Published Oct 5
Evaluated models DeepSeek-V4-Flash , GPT-4o-mini , GPT-4o and others6 Abstract 良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。 。
提出 DART，用去噪表征转移检测多轮智能体攻击并注入提醒
Published Sep 30
Evaluated models Qwen3-8B , Qwen3-14B , Qwen3-32B and others6 提出免训练框架 SED，将有害智能体轨迹蒸馏为可检索安全策略
Published Sep 29
Evaluated models DeepSeek-V4-Flash , GLM-5.2 , Kimi K3 用配对续写与激活修补分析工具智能体越狱后的安全路由
Published Sep 28
Evaluated models Qwen3-14B , Qwen3.5-9B , Qwen3.5-27B and others8 Abstract 越狱后的同一安全反馈在八个工具智能体上分成三条路由，因果集中在最后几层并可作预测基线。这篇工作把越狱上下文残留之后的运行时安全反馈，做成工具智能体上的三路路由问题，并用激活修补给这个路由一个晚层的因果位点。作者认为，反馈可能恢复合法执行、留下未授权动作，或误伤良性流程，而现有攻击、基准和静态护栏没有在固定历史上把这三种结局分开。配对续写因此从同一冻结检查点分别接中性提醒 N 和安全反馈 S，并交叉保留越狱 J+ 与中和越狱 J0。
提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE
Published Sep 28
Evaluated models GPT-5.6 Luna , GPT-5.6 Terra , Gemini 3.8 Flash and others5 Abstract 论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。
提出 Skilder，按角色渐进下发企业工具并确定性拦截越权调用
Published Sep 24
Evaluated models Claude Haiku 4.5 , Qwen 3.5 122B , Gemma 4 31B and others6 Abstract Skilder 用单 MCP 服务器按角色交付工具并硬拦截。Skilder 把企业工具型智能体的能力按角色打包，经一个 MCP 服务器做渐进发现，使工具范围由服务器而不是提示词来执行。
构建 APort Vault 基准，对比支付智能体模型拒答与确定性授权
Published Sep 19
Evaluated models Claude Fable 5.1 , Claude Sonnet 5 , Claude Haiku 4.5 and others14 为冻结模型与目标域自动搜索可部署的 Agent 安全 harness
Published Sep 5
Evaluated models Sonnet 4.6 , GLM-5 , Kimi-K2.5 and others11 提出 SafeEvolve，用轨迹证据协同演化安全 harness 与策略
Published Sep 3
Evaluated models Qwen3.5-4B , Qwen3-4B-Instruct-2507 , Qwen3.5-1.7B and others4 Abstract SafeEvolve 用轨迹证据协同更新安全 harness 和策略，在两个 4B 模型的智能体安全基准上改变安全与效用。SafeEvolve 把已完成的 on-policy 轨迹变成安全 harness 的有界更新，并用两阶段 SFT-RL 把这些更新内化进工具使用策略。
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 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 TRACE 框架，用分解与可演化多轮策略诱导智能体执行有害工作流
Published May 29
Evaluated models Codex , Claude Code , GPT-5.5 and others6 Propose Blindfold, jailbreaking embodied LLMs with action-level manipulation
Published Mar 2
Evaluated models Llama-3.1-8B , DeepSeek-R1-14B , Gemma-3-27B and others8 Abstract Blindfold jailbreaks embodied LLMs with action-level proxy planning, and the authors claim it can bypass semantic checks and is effective in both simulation and real-world settings.Blindfold is a no-box attack against embodied LLM planning modules, rewriting malicious intent into seemingly benign action sequences.
提出 TS-Guard 与 TS-Flow，在执行前检测并引导 Agent 修正有害工具调用
Published Jan 15
Evaluated models GPT-4o , TS-Guard , Qwen2.5-14B-Instruct Abstract TS-Bench 标步骤级风险，TS-Guard 用多任务 RL 做执行前判定，TS-Flow 用反馈代替直接中止。ToolSafe 研究 LLM 智能体在工具执行前的步骤级安全：基准 TS-Bench、护栏 TS-Guard，以及反馈驱动框架 TS-Flow。
提出 Tool Obfuscation 并评测函数调用 Agent 的攻防
Published Jan 14
Evaluated models Qwen3:8B , Llama-3.2:3B , Granite3.2:8B and others5 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。
提出 BrowserART，评测拒答训练在浏览器 Agent 上的泛化
Published Oct 11, 2024
Evaluated models o1-preview , o1-mini , GPT-4o (gpt-4o-2024-08-06) and others8 You have reached the end