Skip to content

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

Oct 12 · Monday

All papers

Found 20 papers

Another 247papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.09469

    Secure-CUA: Constraining the Impact of Untrusted Content in Computer-Use Agents

    提出 Secure-CUA,用动作事务约束计算机使用智能体的不可信影响

    Published
    Setting
    web agent
    Evaluated models
    Claude Opus 5, Gemini 3.8 Flash, GPT-5.6-Sol
    AbstractSecure-CUA 用每步事务约束不可信影响,良性 TSR 接近 Vanilla-CUA。

    Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响,同时保留合法任务所需的不可信信息。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.05640

    Research reveals that the CaMeL defense fails in multi-agent systems and proposes multi-CaMeL

    提出 multi-CaMeL,在智能体调用边界隔离可信指令与非可信数据

    Published
    Evaluated models
    Claude Fable 5, GPT-5.5, GPT-4.1 and others6

    Abstract论文针对多智能体中单体防御不组合的边界清洗问题,提出 multi-CaMeL 协议彻底阻断了 MultiAgentDojo 上的注入攻击。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.03089

    COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks

    提出 COBRA 双 LLM 架构,防御计算机使用 Agent 的分支转向攻击

    Published
    Evaluated models
    gpt-5, UI-TARS-1.5-7B, claude-sonnet-5 and others6

    Abstract提出分支转向防御架构 COBRA,通过事前能力约束与边界代理消除分支转向攻击并兼顾效用。

    Paper analysisRead analysis
  4. 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
  5. DefensesarXiv 2609.05901

    KITA:为 LLM Agent 设计密钥隔离的阈值签名授权架构

    提出 KITA,把 Agent 批准绑定到规范动作的密钥隔离阈值签名

    Published
    Setting
    AI Agent
    AbstractKITA 把隔离的阈值签名当作精确动作的执行条件,并测量门控、相关性与签名开销。

    KITA 是一套密钥隔离的阈值授权架构,用来把模型评审变成执行外部动作的条件。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.02786

    SafeEvolve:基于智能体经验的 Harness-Policy 协同演化安全对齐框架

    提出 SafeEvolve,用轨迹证据协同演化安全 harness 与策略

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen3.5-4B, Qwen3-4B-Instruct-2507, Qwen3.5-1.7B and others4
    AbstractSafeEvolve 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。

    Paper analysisRead analysis
  7. 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
  8. DefensesarXiv 2603.11619

    驯服 OpenClaw:自主 LLM 智能体威胁的安全分析与缓解

    提出对齐五阶段的纵深防御,缓解自主 Agent 跨阶段威胁

    Published
    Setting
    AI Agent
    Abstract这是对 OpenClaw 的生命周期威胁分析与分层缓解设计,案例为定性证据。

    这是对 OpenClaw 的生命周期威胁分析,并配套一套分层缓解设计。要处理的问题是:自主智能体把即时通讯、持久记忆、第三方插件和高权限执行连在一起之后,攻击不再限于单轮越狱,而会跨初始化到执行的多个阶段复合。作者认为只加固单个接口的防御,挡不住这种跨时间攻击。

    Paper analysisRead analysis
  9. DefensesarXiv 2602.10915

    Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

    提出 Aura,用可信内核中介移动 Agent 的身份、感知与动作控制

    Published
    Evaluated models
    Gemini-3-Flash
    AbstractAura mediates structured interactions via the Agent Kernel.

    Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants..

    Paper analysisRead analysis
  10. DefensesarXiv 2602.07918

    CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attribution

    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
    Setting
    AI Agent
    Evaluated models
    Gemini-2.5-Flash, Claude-4.0-Sonnet, Gemini-3-Pro and others4
    AbstractCausalArmor 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.

    Paper analysisRead analysis
You have reached the end