Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter2

Attack technique

Gradient and representation optimization13Automated search48Multi-turn escalation7Encoding and obfuscation16Role-play and persuasion3Reasoning-chain manipulation3Cross-modal payloads11Defense-targeted20Dormant triggers35Selection manipulation11

System type

Models and APIs23LLM applications6AI Agent3

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Attack technique：Role-play and persuasionSystem type：AI AgentClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  1. 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

    arXiv
    2602.07379
    Published
    Layer
    Application layer
    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
  2. AttacksarXiv 2509.22040

    研究：通过编码规则文件对Cursor与GitHub Copilot实施提示注入

    通过规则文件提示注入劫持编码编辑器并执行未授权终端命令

    arXiv
    2509.22040
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Cursor, GitHub Copilot, Claude 4 Sonnet and others4

    Abstract论文提出了针对代码编辑器的提示注入评估框架 AIShellJack，实验显示攻击能诱导 AI 执行未授权终端命令。

    Paper analysisRead analysis
You have reached the end