Skip to content

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

Oct 13 · Tuesday

All papers

Found 6 papers
Filter6

Attack type

Prompt injection5

Defense type

Monitoring and auditing5

System type

AI Agent5

Attack surface / entry point

User input21Web pages and interfaces5Documents and messages8Tool responses15Tool and skill descriptions7Code repositories and dependencies1Weights and gradients1Distribution channels5

Layer

Model layer1Application layer5

System component

MCP and skills9Memory13RAG7Guardrails and judges10Monitors6Reasoning chains4Permissions and sandboxing18Fine-tuning and open weights10Vision10Image generation3Multimodal13
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Web pages and interfacesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Weights and gradientsLayer：Model layerLayer：Application layerSystem component：MonitorsClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  2. 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
  3. DefensesarXiv 2609.35659

    Tracekit：面向自主编码 Agent 的防篡改意图-推理-动作审计系统

    提出 Tracekit，审计编码 Agent 的意图、推理与动作并检测账本篡改

    arXiv
    2609.35659
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Code (claude -p, version 2.1), 独立评审（同一 CLI，无工具）
    AbstractTracekit 把意图、自述和动作写入可锚定的哈希链。

    Tracekit 是无第三方依赖的编码智能体审计层：把人类请求、模型自述和已执行动作并排写入可外部锚定的哈希链，执行前用正则门，事后用规则和独立模型互查。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2609.28915

    研究提出 ACE 语料库，评估内核级证据对 Agent 安全检测的有效性

    构建 ACE 语料，评测内核级证据对 Agent 攻击检测的有效性

    arXiv
    2609.28915
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    AdaBoost, XGBoost, TabPFN and others10
    AbstractACE 用配对的内核与应用层证据表明，syscall 痕迹可判别智能体攻击，两层组合通常更好。

    ACE 是一份把智能体会话的内核 syscall 痕迹与应用层清单、转录配对起来的检测语料和基准。。

    Paper analysisRead analysis
  5. DefensesarXiv 2608.05578

    AMS 工具通过激活分析检测语言模型的安全训练改动

    提出 AMS，用激活分离与方向相似度检测安全训练改动

    arXiv
    2608.05578
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.2-3B-Instruct, Llama-3.2-1B-Instruct and others14
    AbstractAMS 按激活签名把安全改动分四类，前三类可由两级扫描覆盖，行为微调会漏。

    AMS 是面向开放权重模型、部署前使用的激活扫描器，用来看安全训练被拿掉或改写之后，激活空间里还留着什么几何痕迹。

    Paper analysisRead analysis
  6. DefensesarXiv 2602.20708

    ICON：基于推理时纠正的 Agent 间接提示注入防御

    Proposes inference-time defense ICON, which detects attention over-focusing and redirects to correct indirect prompt injection in agents.

    arXiv
    2602.20708
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen-3-8B, Llama-3.1-8B, Mistral-8B and others6
    AbstractICON detects over-focusing and redirects at inference time to balance IPI safety and task utility.

    ICON detects attention over-focusing from IPI at inference time and redirects, avoiding refusal that would terminate the agent trajectory.

    Paper analysisRead analysis
You have reached the end