Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

Agent safety · Papers

Found 14 papers
  1. DefensesarXiv 2610.02861

    论文提出在 Kubernetes 上保护 AI Agent 的七层纵深防御框架与参考架构

    提出 Kubernetes 运维智能体的七层纵深防御框架与参考架构

    Published
    Setting
    AI Agent
    Abstract把运维智能体当不可信租户,用七层控制在完全攻破假设下约束行动。

    把 Kubernetes 上的运维智能体当作不可信租户,在假定提示注入已完全控制其工具选择的前提下,用基础设施重建数据面与控制面的边界。要解决的是:智能体读日志、注解、工单或 MCP 工具描述时,这些内容可以变成它带着自身凭据执行的命令。模型对齐和分类器只降低概率。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.02569

    Pincer:用数字分身学习用户偏好并执行动态最小权限

    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
    Setting
    AI Agent
    Evaluated models
    Claude Haiku 4.5, Muse Spark 1.2 Contributor
    AbstractPincer 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。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.35659

    Tracekit:面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit,审计编码 Agent 的意图、推理与动作并检测账本篡改

    Published
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审(同一 CLI,无工具)
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层:把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链,执行前用正则门,事后用规则和独立模型互查。

    Paper analysisRead analysis
  4. Cave-Bench:虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    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
    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。

    Paper analysisRead analysis
  5. DefensesarXiv 2609.31282

    基于区块链的 Agentic AI 框架:面向安全软件供应链的资源优化与能耗感知

    提出 AttestChain,将供应链安全智能体报告签名上链并据此控制发布

    Published
    Evaluated models
    GPT-class LLM
    AbstractAttestChain 将智能体报告与链上发布门控结合,现有证据来自受控合成构建的总体结果。

    AttestChain 是一个把 LLM 安全检查、智能体身份验证和许可链发布策略连接起来的软件供应链防御框架。。

    Paper analysisRead analysis
  6. DefensesarXiv 2608.21101

    ClawSentry:面向自主 LLM Agent 的渐进式多层安全监控网关

    提出 ClawSentry 多层监控网关,在技能准入和运行时拦截恶意技能与隐藏指令

    Published
    Evaluated models
    Codex/GPT-5.4, Codex/GPT-5.5, Claude Code/GLM-5.1 and others6
    AbstractClawSentry 用包准入、三级运行时门控和反绕过,压低 skill 攻击并保住干净任务。

    ClawSentry 是挂在智能体运行时之外的安全监督网关,用来同时盖住 skill 执行的多个生命周期边界,并把已被拒绝的效果记到会话里。

    Paper analysisRead analysis
  7. Abstract论文系统揭示了智能体基准的奖励作弊隐患,提出自动化红队审计与迭代修补系统 BENCHJACK。

    论文系统研究了主流 AI 智能体基准评测中的奖励作弊问题,提出了首个针对基准缺陷的自动化红队审计与生成对抗式迭代修补系统 BENCHJACK。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.12644

    Revealing security threats and defense architectures for autonomous agents: an OpenClaw case study

    Reviews threats to autonomous agents and proposes a full-lifecycle defense blueprint, FASA

    Published
    Setting
    AI Agent
    AbstractUsing 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.

    Paper analysisRead analysis
  9. DefensesarXiv 2603.11619

    Taming OpenClaw: Security Analysis and Mitigation of Threats in Autonomous LLM Agents

    Proposes a defense-in-depth aligned with the five stages to mitigate cross-stage threats to autonomous agents

    Published
    Setting
    AI Agent
    AbstractThis is a lifecycle threat analysis and layered mitigation design for OpenClaw, with the cases serving as qualitative evidence.

    This is a lifecycle threat analysis of OpenClaw, accompanied by a set of layered mitigation designs. The problem addressed is: when autonomous agents connect instant messaging, persistent memory, third-party plugins, and high-privilege execution, attacks are no longer limited to single-turn jailbreaks but can compound across multiple stages from initialization to execution. The authors argue that defenses hardening only individual interfaces cannot stop such cross-temporal attacks.

    Paper analysisRead analysis
You have reached the end