Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Attack type

Jailbreaks7Prompt injection32Poisoning and backdoors20Detection evasion6Malicious use0

Attack technique

Automated search7Multi-turn escalation5Defense-targeted5

Impact

Unauthorized actions4

System type

AI Agent7coding agent3

Attacker access

Black-box5

Attack surface / entry point

User input7Tool responses4

Layer

Prompt layer42Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksAttack type：Malicious useAttack technique：Automated searchLayer：Application layerClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.05943

    CRIME 框架利用良性 Agent 技能组合诱发恶意行为

    提出 CRIME 框架，组合良性 Agent 技能诱发恶意行为

    arXiv
    2610.05943
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-4o-mini, GPT-4o and others6
    Abstract良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。

    CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。。

    Paper analysisRead analysis
  2. AttacksarXiv 2608.27439

    RedEvoAgent：以经验驱动技能演化的自动红队智能体

    提出 RedEvoAgent，演化攻击技能对黑盒智能体做自动红队

    arXiv
    2608.27439
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    MiniMax-M2.5, DeepSeek-V4-Flash, Qwen3.5-35B
    AbstractRedEvoAgent 用验证棘轮演化可读攻击技能，在两种产品级 harness 上多数设置高于固定工具与红队基线。

    RedEvoAgent 是面向产品级 black-box 智能体的自动红队方法，用一份可演化、人类可读的攻击技能编排多个越狱工具。。

    Paper analysisRead analysis
  4. AttacksarXiv 2607.11698

    AHA 用自动研究循环发现生产 Agent 漏洞概念

    提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念

    arXiv
    2607.11698
    Published
    Layer
    Application layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    Minimax-M2.7, Kimi-K2.6, Deepseek-V4-Pro and others5
    Abstract论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。

    AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。

    Paper analysisRead analysis
  6. AttacksarXiv 2601.05466

    Jailbreaking large language models through reinforcement learning with iterative tool disguise attacks

    提出 iMIST，用工具伪装和 PPO 迭代越狱大语言模型

    arXiv
    2601.05466
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    DeepSeek-V3, Qwen3-32B, GPT-OSS-120B
    AbstractiMIST 用工具伪装和在线 PPO 做黑盒越狱，Table I 中 JADES 高于同格基线。

    iMIST是黑盒越狱方法：把恶意查询伪装成合法工具调用，再用在线强化学习把响应的有害性分数往上推。

    Paper analysisRead analysis
You have reached the end