Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Attack type

Jailbreaks6

Impact

Harmful content6Unauthorized actions7Data and privacy leaks4

System type

Models and APIs91AI Agent6

Attacker access

Black-box6

Attack surface / entry point

User input6

Layer

Application layer4

System component

Guardrails and judges3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Impact：Harmful contentSystem type：AI AgentAttacker access：Black-boxClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.08678

    研究揭示投机解码的安全代价并提出 SecureSD 加固方法

    测量有损投机解码的安全代价，并提出 SecureSD 收紧早期验证

    arXiv
    2610.08678
    Published
    Layer
    Model layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    Qwen3-8B, Qwen3-32B, Llama-3.1-8B-Instruct and others6
    Abstract有损推测解码的早期偏离更快抬高越狱与注入风险。

    作者研究有损推测解码在换取速度时，是否会比效用更快地损害越狱与提示注入防护，并给出按位置校正的 SecureSD。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.03434

    Persona Guardrail：面向智能体系统的生产级防御框架

    提出 Persona Guardrail，强制客服智能体守住功能边界

    arXiv
    2610.03434
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Evaluated models
    Qwen3-30B-A3B, Qwen3-VL-30B, Qwen3-8B and others5
    AbstractPersona Guardrail 用功能边界做同步输入输出校验，并在 PAGE 与生产延迟预算下给出评测。

    Persona Guardrail 是客服向智能体的同步运行时防御：先写明功能边界，再决定放行或拦截，而不是只检测某一攻击类。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.09798

    CS-Guard：首个面向代码生成安全的 LLM 护栏评测基准

    提出 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御

    arXiv
    2609.09798
    Published
    Layer
    Prompt layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    CodeLlama-13B-Instruct, DeepSeekCoder-V2-Lite-16B, GPT-OSS-20B and others7

    Abstract论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。

    Paper analysisRead analysis
  4. 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