Skip to content

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

Oct 12 · Monday

Jailbreaks and attacks · Papers

Found 1 paper
Filter2

Attack technique

Automated search5Multi-turn escalation5Conversation structure manipulation1Defense-targeted5

System type

Models and APIs6AI Agent1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Attack technique：Conversation structure manipulationSystem type：AI AgentTopic: Jailbreaks and attacksClear all
  1. 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