Skip to content

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

Oct 13 · Tuesday

All papers

Found 8 papers
Filter5

Attack type

Jailbreaks8Prompt injection55Poisoning and backdoors37Extraction and theft3Malicious use6

Attack technique

Automated search3

Impact

Harmful content5Unauthorized actions3

System type

Models and APIs0LLM applications3AI Agent37coding agent5Multi-agent systems3

Attack surface / entry point

User input8

Layer

Prompt layer161Model layer39Application layer8Training and data layer17
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksSystem type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsLayer：Application layerClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  1. 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
  2. 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
  3. AttacksarXiv 2607.03968

    The study reveals workflow-level jailbreaks in IDE programming agents: GitHub Copilot generated harmful content across four backends at 816/816

    提出工作流级越狱，让编程 Agent 在开发任务中写入有害示例

    arXiv
    2607.03968
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, Gemini 3.1 Pro and others4
    Abstract作者报告 Copilot 后端会在编码工作流中生成其在单轮条件下通常拒绝的有害答案。

    这是一项生产 IDE 编码智能体的工作流越狱研究，受测对象是 Copilot 的四个模型后端，而非评测流水线中的名义目标。

    Paper analysisRead analysis
  4. DefensesarXiv 2606.08234

    SciTrace：面向科学发现智能体的轨迹感知安全推理框架

    提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验

    arXiv
    2606.08234
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
    AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。

    SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2510.01359

    JAWS-Bench：研究者用三种工作区场景系统越狱代码 Agent

    提出 JAWS-Bench，评测代码 Agent 在三级工作区中的越狱与恶意代码可执行性

    arXiv
    2510.01359
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4.1, GPT-o1, DeepSeek-R1 and others8

    Abstract论文提出了评估代码智能体端到端恶意代码越狱的 JAWS-Bench，发现多文件与智能体推理会明显放大可部署危害。

    Paper analysisRead analysis
  8. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end