Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter5

Attack type

Jailbreaks5Prompt injection111Poisoning and backdoors25Detection evasion8Malicious use3

System type

AI Agent4

Attacker access

Black-box3

Attack surface / entry point

User input38Web pages and interfaces1Documents and messages2Tool responses13Tool and skill descriptions3Images, audio and video2

Layer

Prompt layer40Model layer5Application layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesAttack surface / entry point：Images, audio and videoLayer：Application layerClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. 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