Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Attack type

Jailbreaks2Prompt injection4

Attack technique

Gradient and representation optimization4Automated search7Multi-turn escalation5Conversation structure manipulation2Defense-targeted6

Layer

Prompt layer8Model layer1Application layer1
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：JailbreaksAttack technique：Conversation structure manipulationLayer：Model layerLayer：Application layerClear all

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

  1. InterpretabilityarXiv 2603.08234

    续写与拒答之争：大语言模型中续写触发越狱的机制分析

    分析续写触发越狱的注意力头机制并提出 HCS

    arXiv
    2603.08234
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-2-7B-Chat, Qwen2.5-7B-Instruct
    Abstract作者称越狱来自两类头竞争，HCS 加蒸馏可把该竞争用于推理时干预。

    作者用注意力头机制分析 continuation-triggered jailbreak：同一有害指令下，把 continuation 后缀从指令后面挪到提示词边界外，模型更容易顺着后缀继续生成。

    Paper analysisRead analysis
  2. AttacksarXiv 2509.25624

    STAC：看似无害的工具调用链如何攻破 LLM Agent

    提出 STAC 框架，把恶意目标拆成多轮看似无害的工具调用链

    arXiv
    2509.25624
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    GPT-4.1-2025-04-14, GPT-4.1-mini-2025-04-14, Qwen3-32B and others8

    Abstract作者提出并验证了智能体在序列化工具攻击下的普遍脆弱性，指出针对累积动作序列防御的必要性。

    Paper analysisRead analysis
You have reached the end