Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Jailbreaks27Prompt injection23Poisoning and backdoors51Extraction and theft3

Attack technique

Automated search6Multi-turn escalation2Role-play and persuasion3Side channels4Dormant triggers1

Attack surface / entry point

User input3
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.
Attack type：Extraction and theftAttack technique：Multi-turn escalationAttack technique：Dormant triggersClear all

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

  1. AttacksarXiv 2609.33985

    研究：众包微调数据投毒可放大专有指令抽取

    提出主题锚点投毒，放大众包微调后的专有指令提取

    arXiv
    2609.33985
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-14B-Instruct, Llama-3.1-8B-Instruct and others4

    Abstract论文提出基于主题锚点的数据中毒攻击，证明低比例的中毒样本可在黑盒条件下隐蔽放大微调指令泄漏。

    Paper analysisRead analysis
  2. 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
You have reached the end