Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 4 papers
Filter3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
  1. 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
  2. DefensesarXiv 2603.14707

    视觉混淆代理:利用与防御计算机使用智能体的感知失效

    提出进程外双通道对比分类,拦截计算机使用智能体的错误点击

    Published
    Evaluated models
    multi-modal-embed-small
    Abstract感知错误可被屏幕像素对调利用。

    作者把 CUA 的感知失败写成安全漏洞visual confused deputy:智能体按看错的屏幕授权 click(x,y),真实落点与它以为的元素不一致。

    Paper analysisRead analysis
  3. 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 以 Agent Kernel 中介结构化交互。

    Aura 用内核中介的结构化智能体交互,替换以屏幕为接口的移动助手。。

    Paper analysisRead analysis
  4. 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 红队评测三类语音智能体:查询式访问消掉认证与泄密成功,行为类攻击仍在。

    Aegis 用多轮红队评测已接入业务系统的 ALLM 语音智能体。作者称这是该设定下的 the first systematic red-teaming framework。

    Paper analysisRead analysis
You have reached the end