Skip to content

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

Oct 12 · Monday

All papers

Found 13 papers
Filter4

Attack type

Prompt injection6Poisoning and backdoors3

Defense type

Model hardening5Inference-time intervention5Detection and filtering31Instruction–data separation13Permissions and approval17Monitoring and auditing20

Impact

Unauthorized actions5Data and privacy leaks3Output manipulation4

System type

Models and APIs8LLM applications5AI Agent49coding agent5web agent6Browser and computer use3Multi-agent systems4

Attack surface / entry point

Web pages and interfaces4Documents and messages3Tool and skill descriptions3

Layer

Application layer12

System component

MCP and skills3Permissions and sandboxing3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationSystem type：LLM applicationsSystem type：coding agentSystem type：Browser and computer useClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.11634

    LTBD：用可学习信任边界分隔符防御提示注入

    提出 LTBD，用可学习分隔符隔离可信指令与不可信数据

    arXiv
    2610.11634
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama3-8B-Instruct, Llama3.1-8B-Instruct, Falcon3-7B-Instruct and others4
    AbstractLTBD 只训练四个分隔符嵌入。

    LTBD 是一种不改基座权重的提示注入防御：只学习用来标出可信指令与不可信数据边界的四个 token 嵌入。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.05826

    研究者提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    提出临时可见性协议，限制持续摄入 RAG 向量库的投毒暴露

    arXiv
    2610.05826
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Abstract用截止期限制未核验可见时长。

    这篇工作给持续摄入的 RAG 向量库一个失败关闭的临时可见性协议，把协议能限制的未核验暴露和依赖检测器的中毒暴露分开。

    Paper analysisRead analysis
  4. Analysis and theoryarXiv 2610.04375

    Paper reveals that LLM agent tool calls are rewritten during execution paths, and proposes IntAct as a fix

    提出 IEC 与 IntAct，测量并修复 Agent 工具调用的路径篡改

    arXiv
    2610.04375
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    qwen3-coder-plus, Qwen2.5-Coder-32B, Qwen2.5-72B and others4

    Abstract论文界定工具调用在执行路径中的意图偏离问题，提出无执行归因协议与跳级修复，为智能体工程提供评测与设计准则。

    Paper analysisRead analysis
  5. DefensesarXiv 2610.03089

    COBRA: A Dual-LLM Architecture for Defending Computer-Using Agents Against Branch-Jumping Attacks

    提出 COBRA 双 LLM 架构，防御计算机使用 Agent 的分支转向攻击

    arXiv
    2610.03089
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    gpt-5, UI-TARS-1.5-7B, claude-sonnet-5 and others6

    Abstract提出分支转向防御架构 COBRA，通过事前能力约束与边界代理消除分支转向攻击并兼顾效用。

    Paper analysisRead analysis
  8. DefensesarXiv 2609.19587

    红队测试 Auto Mode：用注入与多上下文攻击绕过编码 Agent 阻断监控器

    提出 Auto Mode ++，加固编码 Agent 阻断监视器

    arXiv
    2609.19587
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Opus 5, Opus 4.8, Opus 4.7 and others8

    Abstract系统评估生产阻断监视器在面对持续恶意智能体时的表现，提出加固防御并指明多上下文防御挑战。

    Paper analysisRead analysis
  9. DefensesarXiv 2609.10992

    拆解 LLM 交互中的隐私-效用权衡：Veilmind-4B 意图驱动本地保护框架

    提出意图驱动本地框架 Veilmind，净化发往远程模型的提示词

    arXiv
    2609.10992
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Veilmind-4B
    Abstract本地模型按意图净化提示词，在 Uprise 上给出两个隐私-效用工作点。

    本地侧的意图驱动净化，用来降低用户提示词发往不受信任远程模型时的敏感属性暴露。

    Paper analysisRead analysis
  11. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  12. DefensesarXiv 2605.08382

    SecureForge 通过提示词优化发现并减少 LLM 生成代码漏洞

    提出 SecureForge，在推理时优化系统提示以减少编码智能体的代码弱点

    arXiv
    2605.08382
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Qwen 2.5 Coder 7B, Qwen 2.5 Coder 14B, Qwen3 30B-A3B and others10
    AbstractSecureForge 审计良性 CWE 失败并优化系统提示词。

    SecureForge是一条只用 API 和静态分析、在推理时加固编码模型的流水线。

    Paper analysisRead analysis
  13. DefensesarXiv 2602.10915

    Blind Gods and Broken Screens: Building a Secure, Intent-Centric Mobile Agent Operating System

    提出 Aura，用可信内核中介移动 Agent 的身份、感知与动作控制

    arXiv
    2602.10915
    Published
    Layer
    Application layer
    Setting
    Browser and computer use
    Evaluated models
    Gemini-3-Flash
    AbstractAura mediates structured interactions via the Agent Kernel.

    Aura uses kernel-mediated structured agent interaction, replacing screen-interface mobile assistants..

    Paper analysisRead analysis
You have reached the end