Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

Attack type

Jailbreaks4Prompt injection37Poisoning and backdoors11

Defense type

Detection and filtering6Instruction–data separation4Permissions and approval5Monitoring and auditing4

Impact

Unauthorized actions3

System type

AI Agent4

Attack surface / entry point

User input4Tool responses3

Layer

Prompt layer5Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksDefense type：Instruction–data separationLayer：Application layerClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.14003

    FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露

    提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露

    arXiv
    2609.14003
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5

    Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。

    Paper analysisRead analysis
  4. 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

    arXiv
    2609.02786
    Published
    Layer
    Application layer
    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
You have reached the end