Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 16 papers Another 232 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 PACE,在工具调用前做路径隔离与效果授权
Published Oct 1
Evaluated models gpt-5.6-luna , DeepSeek-V4-Flash , Qwen-3.8-27B Abstract PACE 在工具边界做路径割与效果核验。PACE 是面向工具调用型 LLM 智能体的运行时调解:当准入证据无法区分会改变行为的规格时,不在出口站点上撤销调解,而在最后一次工具调用前同时检查表示出的影响路径和请求权限。
提出 ZoneClaw,用记忆分区防御计算机使用 Agent 的持久记忆攻击
Published Oct 1
Evaluated models Claude Sonnet 4.6 , GPT-5.5 , GLM-5.2 and others4 为 Agent 提出资源层授权系统 Pincer,用数字分身执行动态最小权限
Published Oct 1
Evaluated models Claude Haiku 4.5 , Muse Spark 1.2 Contributor Abstract Pincer 在资源层以三票合取做授权。Pincer 是加在现成 coding agent 上的资源层授权防御:用只受用户侧信息影响的 digital twin 做动态最小权限,并与 tool-call 层防御并存。要处理的是用户维护策略带来的权限蠕变和授权疲劳,以及不学习用户策略的 tool-call 分类器。作者引述工作称 auto mode 会放行多数不安全操作,并认为推理代码或复杂 shell 的效果在这一层不实际。
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 提出 Pictionary,将不可信文本渲染成图像以防御提示注入
Published Sep 29
Evaluated models Claude Opus 4.7 , Claude Haiku 4.5 , GPT-5.5 and others12 提出并评测保险库中介执行边界,隔离 Agent 的 API 凭据
Published Sep 27
Evaluated models Corvic Security Vault Abstract 作者称,凭据分离可减少披露路径,但权限、操作授权和配置验证仍需独立控制。这是一项智能体 API 凭据威胁分析及 Vault 执行边界的功能评测。 作者关心的不是模型能否承诺保密,而是认证材料是否会进入模型、日志、记忆和执行代码。
提出多智能体系统提示注入的威胁模型与四层架构防御
Published Sep 19
Evaluated models GPT-4o (2024-08-06) , Claude 3.5 Sonnet , Llama 3 70B-Instruct 提出 IntentCap,按来源字段所有权合成并裁决 Agent 能力租约
Published Sep 14 Abstract 四源字段租约约束副作用。IntentCap 是把智能体能力绑到当前任务意图、并按上下文来源划分字段所有权的权限机制。
提出 FLOWSEAL,用工具级信息流控制阻断智能体隐私泄露
Published Sep 12
Evaluated models DeepSeek-V3.2 , GPT-4.1-mini , Gemini-Flash-2.5 Abstract 作者分析大模型智能体隐私检查与攻击面重合问题,提出外部拦截防御 FLOWSEAL 并验证有效性。
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 AgentKernel,用四支柱强制中介 Agent 的输入、工具与记忆
Published Aug 29 Abstract AgentKernel 是四支柱智能体 OS 设计,安全论证未附带实测数字。AgentKernel 是把安全做成组织原则的智能体 OS 架构,不是带跑分的攻防评测。
提出 TMA-NM,以写时来源绑定抵御 Agent 长期记忆投毒
Published Jun 23
Evaluated models gpt-5-chat , gpt-4o-mini , claude-opus-4.1 and others8 Abstract TMA-NM 用来源绑定的行动权限挡住记忆洗白。TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源,用来挡住跨会话记忆投毒。
Reviews threats to autonomous agents and proposes a full-lifecycle defense blueprint, FASA
Published Mar 13 Abstract Using OpenClaw as an example, it divides risks into three layers and uses FASA to describe defense from input to system execution.This is a threat review and defense architecture report using OpenClaw as a case study, not a scored attack or defense evaluation.
提出间接提示注入护栏 CausalArmor,按因果归因选择性清洗未受信片段
Published Feb 8
Evaluated models Gemini-2.5-Flash , Claude-4.0-Sonnet , Gemini-3-Pro and others4 Abstract CausalArmor selectively sanitizes and masks chain of thought at privileged decisions based on attribution margins, to mitigate over-defense against IPI.CausalArmor is an indirect prompt injection defense middleware on tool-calling agents, used to avoid paying the utility and latency costs of always-on sanitization even when there is no attack.
Defenses arXiv 2312.06632 · Dec 12, 2023 提出 SciGuard 外部护栏与 SciMT 基准,控制化学科学 AI 误用
Published Dec 12, 2023
Evaluated models SciGuard (GPT-4) , SciGuard (Gemini) , SciGuard (Mixtral) and others5 Abstract SciGuard 以外部智能体控制化学 AI 误用。这篇工作把化学科学 AI 的误用控制做成外部智能体,而不是改模型权重。作者担心合成规划、毒性预测和科学语言模型被用来获取有害物质信息、规避监管或传播危险知识,同时合法工业用途又不能靠一律拒绝来处理。SciGuard 由 LLM 担任中介,把原则和指南放进短期记忆,把分子库、危害库、法规和交互历史放进可检索的长期记忆,再按 Chain of Thought 调用 Chemprop、LocalRetro 等工具,或用 RAG 补法规片段,最后回答、追问或拒绝。
You have reached the end