Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 11 papers
Filter4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
  1. 研究提出 Agent 安全新维度:识别未履行的安全义务

    提出义务识别基准 ObligationBench,并训练护栏识别 Agent 未履行的安全义务

    Published
    Evaluated models
    ObligationGuard, Claude-Opus-4.8, GPT-5.6-Sol and others17
    Abstract义务是护栏缺口。

    作者认为编码智能体的安全不能只靠拦截禁止动作,还要找出终止时仍未做的安全关键动作,并将其称为义务。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER,以确定性检查优先拦截多智能体流水线的内容攻击

    Published
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里,确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  3. 论文实测 Agent 工具调用门控栈的失败相关性

    提出 nmult 并评测 Agent 动作门禁堆叠的错误相关性

    Published
    Setting
    AI Agent
    Evaluated models
    AgentTrust runtime (174 rules), GPT-5.5 (gpt55), claude-haiku-4-5-20251001 and others7
    Abstract论文实测发现大模型裁判间错误显著相关,作者主张按机制选型并在整栈层面度量防护增益。

    论文是一项针对智能体动作拦截防御堆叠故障关联性与实际组合价值的实证测量研究。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.02432

    论文提出 LLM 输入扰动鲁棒性度量,并发布 ASA 攻击与 AttestMCP 防护

    提出 ASA 与 AttestMCP,度量并降低 LLM 对输入序列扰动的敏感

    Published
    Attacker
    Black-box
    Evaluated models
    Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
    Paper analysisRead analysis
  5. VoxParity 评测:语音智能体在需要听声判断时仍按文字行事

    提出 VoxParity,固定转写只改音频,评测语音智能体是否按行业规则改工具调用

    Published
    Setting
    AI Agent
    Evaluated models
    MiMo-V2.6-Pro, gemini-3.7-flash, Qwen3.8-Omni and others15
    AbstractVoxParity 用固定转写的音频对比和 words-only null,测量语音智能体是否按所听内容改变工具调用。

    VoxParity 测量语音智能体在词语不变、只有声音改变时,是否按行业规则改它所执行的工具调用。

    Paper analysisRead analysis
  6. JEV 作为智能体轨迹安全评判器:与生成式 LLM 评判器的实证对比

    对比类型化评审与生成式评审对智能体轨迹的安全判定

    Published
    Setting
    AI Agent
    Evaluated models
    JEV, GLM-5.2-Tencent, DeepSeek-V4-Flash and others5
    AbstractJEV 的四基准平均正类 F1 最高,延迟和估计费用更低,但分数据集与精确率有取舍。

    在已保存的工具使用智能体轨迹上,比较类型化评审 JEV 与四种生成式评审的回溯安全分类。

    Paper analysisRead analysis
  7. Agentic Commerce Bench:衡量会花钱的智能体的欺诈检测能力

    构建支付欺诈基准 ACB,评测花钱智能体的欺诈检测

    Published
    Setting
    AI Agent
    Evaluated models
    gordonguard, pattern judge
    AbstractACB 把支付欺诈与智能体操纵分开测量,作者强调观察权限、误报预算和微支付复核成本。

    ACB 是一套智能体支付欺诈基准与检测参考栈,目标是衡量钱是否被不当提取,而不仅是智能体是否接受了恶意指令。

    Paper analysisRead analysis
  8. DefensesarXiv 2603.14707

    Visual Confusion Agents: Exploiting and Defending Against Perception Failures in Computer-Use Agents

    Proposes out-of-process dual-channel comparison classification to intercept erroneous clicks by computer-use agents

    Published
    Evaluated models
    multi-modal-embed-small
    AbstractPerception errors can be exploited by swapping screen pixels.

    The authors frame CUA's perception failure as a security vulnerability, visual confused deputy: the agent authorizes click(x,y) based on a misread screen, and the actual landing point differs from the element it believes it is clicking.

    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. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    提出 Aegis 红队框架,多轮攻击高风险语音 Agent

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.

    Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.

    Paper analysisRead analysis
You have reached the end