Skip to content

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

Oct 12 · Monday

Jailbreaks and attacks · Papers

Found 3 papers
Filter3

Attack type

Jailbreaks3

Attack technique

Automated search5Multi-turn escalation5Encoding and obfuscation2Conversation structure manipulation1Defense-targeted5

System type

Models and APIs38AI Agent3

Attack surface / entry point

User input3

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack technique：Encoding and obfuscationAttack technique：Conversation structure manipulationSystem type：AI AgentTopic: Jailbreaks and attacksClear all
  1. AttacksarXiv 2603.01414

    通过动作级操纵越狱具身 LLM

    提出 Blindfold，用动作级操纵越狱具身 LLM

    arXiv
    2603.01414
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    No-box (offline transfer)
    Evaluated models
    Llama-3.1-8B, DeepSeek-R1-14B, Gemma-3-27B and others8
    AbstractBlindfold 以动作级代理规划越狱具身 LLM，作者称可绕过语义检查并在仿真与真机生效。

    Blindfold 是面向具身 LLM 规划模块的 no-box 攻击，把恶意意图改写成看似良性的动作序列。

    Paper analysisRead analysis
  3. 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