Skip to content

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

Oct 12 · Monday

All papers

Found 11 papers
Filter3

Attack type

Jailbreaks3Prompt injection11Poisoning and backdoors4Detection evasion11

Defense type

Detection and filtering5

Impact

Harmful content3Unauthorized actions11Output manipulation11

System type

LLM applications7AI Agent6

Attack surface / entry point

User input5Retrieval corpus3

Layer

Application layer11

System component

MCP and skills4Memory10RAG8Guardrails and judges11Reasoning chains3Vision9Multimodal10
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.
Attack type：Prompt injectionImpact：Output manipulationSystem component：Guardrails and judgesClear all

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

  1. DefensesarXiv 2610.04412

    论文研究 LLM 数字孪生参与增强民主时的提示注入脆弱性

    提出检测、结构化与 GSPO 流程，降低共识生成的提示注入错位

    arXiv
    2610.04412
    Published
    Layer
    Application layer
    Setting
    LLM applications, Multi-agent systems
    Evaluated models
    LLaMA-2 7B, LLaMA-3 8B, GPT 3.5 Turbo and others14
    Abstract三章依次做个体偏好预测、政党知识图谱审议，以及共识生成对提示注入的脆弱性与一条防御流程。

    这是一篇把 LLM 数字孪生放进增强民主的博士论文，分个体表示、政党聚合和共识生成的提示注入三章。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.02432

    论文提出 LLM 输入扰动鲁棒性度量，并发布 ASA 攻击与 AttestMCP 防护

    提出 ASA 与 AttestMCP，度量并降低 LLM 对输入序列扰动的敏感

    arXiv
    2610.02432
    Published
    Layer
    Application layer
    Setting
    LLM applications, AI Agent
    Attacker
    Black-box
    Evaluated models
    Gemma-3-27B-Instruct, Gemma-3-4B-Instruct, Llama-3.2-3B-Instruct and others12
    Paper analysisRead analysis
  3. AttacksarXiv 2609.30383

    研究者提出技能级联攻击

    提出技能级联攻击，把有害目标拆散到多个技能里绕过单技能扫描

    arXiv
    2609.30383
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.4 Mini, Claude Opus 4.6 and others11

    Abstract论文探讨了多技能智能体系统面临的技能级联攻击风险，提出自动化红队框架与基准集，指出跨技能交互存在安全防护盲区。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.02316

    Counter-GEO-Bench：现有护栏难挡 GEO 虚假信息

    构建 COUNTER-GEO-BENCH，评测生成式搜索中的 GEO 虚假信息防御

    arXiv
    2609.02316
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Gemma-4-31B-IT, Qwen-3.5-35B-A3B, Llama-4-Scout-17B-16E and others8

    Abstract论文构建了针对 GEO 虚假信息的首个防御基准，揭示通用护栏的失效与反作用，并提出了有效的轻量对比检测基线。

    Paper analysisRead analysis
  7. AttacksarXiv 2607.14493

    LogInject 框架披露 LLM 日志分析中的被动提示注入

    提出 LogInject 框架，评测日志分析中的被动提示注入及缓解

    arXiv
    2607.14493
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    GPT-4o, Claude 3.5 Sonnet, Llama-3-70B-Instruct

    Abstract论文评估了 LLM 日志分析中的上下文污染风险，提出分片拼接等攻击与三层防御，指出必须结合架构隔离与人工介入。

    Paper analysisRead analysis
  9. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
  10. AttacksarXiv 2601.21360

    Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation

    提出 AST-ASIP ，把对抗指令植入编译器忽略区域以劫持代码评分

    arXiv
    2601.21360
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    DeepSeek-V3.2, Qwen3-235B, GPT-OSS-120B and others9
    Abstract作者称 RLHF 的服从性使评分脱离代码。

    这篇工作把自动代码评分中的失败称为 Compliance Paradox：评分模型可以离开提交逻辑，转而执行嵌在可编译代码里的隐藏指令。

    Paper analysisRead analysis
You have reached the end