Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter5

Attack type

Jailbreaks3Prompt injection74Poisoning and backdoors16Detection evasion5Malicious use2

Defense type

Detection and filtering3

Impact

Unauthorized actions3

System type

LLM applications3AI Agent4

Attack surface / entry point

User input22Web pages and interfaces4Documents and messages6Tool responses6Tool and skill descriptions5Code repositories and dependencies3Images, audio and video3Distribution channels3

Layer

Prompt layer14Model layer11Application layer7Training and data layer5

System component

Guardrails and judges3Multimodal3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack type：Detection evasionAttack type：Malicious useAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Images, audio and videoLayer：Application layerClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    arXiv
    2610.09793
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击，但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.05870

    MBZUAI 提出可校准的真实图像认证方法

    提出校准重合成方法，以生成器反演保真度认证真实图像并防御对抗扰动

    arXiv
    2610.05870
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    White-box

    Abstract论文提出基于反演保真度与阈值校准的健全认证框架，在对抗扰动下维持错误率界限，并指出真实内容可认证性随生成器演进而萎缩。

    Paper analysisRead analysis
  4. DefensesarXiv 2607.13716

    CAVA：面向智能体 AI 运行时治理的规范动作验证与证明

    提出 CAVA，将异构智能体运行时事件规范为可哈希动作并绑定审批与回执

    arXiv
    2607.13716
    Published
    Layer
    Application layer
    Setting
    AI Agent
    AbstractCAVA 用规范动作指纹承接异构运行时治理。

    CAVA 是给异构智能体运行时用的动作语义层，用来回答“被批准和被审计的到底是哪一个动作”。

    Paper analysisRead analysis
  5. DefensesarXiv 2603.01544

    RA-Det：利用鲁棒性不对称检测 AI 生成图像

    提出 RA-Det，利用鲁棒性不对称检测 AI 生成图像

    arXiv
    2603.01544
    Published
    Layer
    Application layer
    Setting
    LLM applications
    AbstractRA-Det 把扰动下特征漂移差变成检测信号，平均 ACC 高于表中通用检测器，但不是每行最高。

    RA-Det 是合成图像检测器，用扰动下的表示稳定性差异代替外观痕迹。

    Paper analysisRead analysis
  6. AttacksarXiv 2602.05484

    Masked Mirror: Covert Prompt Injection Attacks Against LLM-Based Phishing Detection

    提出隐蔽提示注入攻击 LLM 钓鱼检测器，并给出防御 InjectDefuser

    arXiv
    2602.05484
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    OpenAI GPT-5, xAI Grok 4 Fast (Non-Reasoning), Meta Llama 4 Maverick and others4
    Paper analysisRead analysis
  7. AttacksarXiv 2505.23266

    AdvOF：用对抗物体融合攻击 VLM 驱动的视觉语言导航智能体

    提出 AdvOF，生成对抗物体误导视觉语言导航智能体的场景感知

    arXiv
    2505.23266
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Attacker
    White-box
    Evaluated models
    Lseg, Clip, ViT-L/16 and others5
    AbstractAdvOF 以多视角融合生成对抗物体。

    AdvOF 是针对 VLM 驱动 VLN 服务导航的对抗物体攻击。

    Paper analysisRead analysis
You have reached the end