Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter3

Impact

Unauthorized actions41Data and privacy leaks13Output manipulation23Availability and reliability5Oversight failure3

System type

AI Agent3

Attack surface / entry point

User input9Web pages and interfaces3Tool and skill descriptions3Images, audio and video5Training data7Weights and gradients3Distribution channels4Inference services and hardware2

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Inference services and hardwareClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  3. Evaluation and benchmarksarXiv 2609.19140

    AgentLSD：在对抗性任务污染下评测 AI 安全 Agent

    评测安全 Agent 在对抗性任务污染下的解题成功与开销

    arXiv
    2609.19140
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Gemma-4 31B, DeepSeek-V4 Flash, GPT-OSS 120B and others6
    AbstractAgentLSD 用配对 web CTF 表明，欺骗性环境证据会改变安全智能体的解题率与工作量。

    AgentLSD 是一个对照框架，用来测量安全智能体在任务本身不变时，对对抗性任务污染的反应。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.30040

    研究揭示 LLM 按 token 计费可被服务商系统性虚报

    构造可通过计费审计的 token 虚报，使服务商系统性超收

    arXiv
    2605.30040
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    PALACE domain-adapted auditor
    Abstract不诚实提供方可在三种 token 审计上虚报并通过检查，作者认为需改用提供方不控制的证据。

    不透明 LLM 的按 token 计费里，现有审计核验的是提供方可控的证据，不诚实提供方可以虚报并通过检查。。

    Paper analysisRead analysis
You have reached the end