Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter6

Attack type

Prompt injection5

Defense type

Detection and filtering4

Impact

Unauthorized actions4

System type

Models and APIs3LLM applications6AI Agent7coding agent1

Attack surface / entry point

User input20Web pages and interfaces4Documents and messages5Tool responses8Tool and skill descriptions10Code repositories and dependencies3Memory writes3Inter-agent messages3Images, audio and video3Training data1Distribution channels6

Layer

Application layer6

System component

MCP and skills9Memory16Guardrails and judges7Monitors8Reasoning chains4Permissions and sandboxing15Fine-tuning and open weights4Vision3Multimodal4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 227papers have no tags yet and are not included in filtered results.
System type：AI AgentSystem type：coding agentAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Training dataSystem component：Guardrails and judgesClear all

Another 227papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.30657

    研究者提出面向邮件 Agent 的攻击链建模提示注入检测框架

    提出面向邮件 Agent 的攻击链提示注入检测框架

    arXiv
    2609.30657
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Proposed framework
    Abstract攻击链与动作一致性融合改善了严格检测的平均 F1，但迁移、误报和攻击召回仍需分别看。

    这是一项邮件智能体提示注入防御的离线建模与评测研究：作者把攻击文本是否恶意、攻击是否推进到工具操作、最终参数是否达标分开处理。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.22510

    特拉维夫大学提出爆炸性提示词：条件触发的间接提示注入可绕过九款生产 Agent

    提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse

    arXiv
    2609.22510
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Llama-3.1-8B-Instruct, Llama-3.1-70B-Instruct, Qwen2.5-32B-Instruct and others15
    Abstract论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。

    论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。

    Paper analysisRead analysis
  4. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  5. DefensesarXiv 2603.04474

    From Spark to Wildfire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

    Proposing a lineage-graph governance layer to suppress error cascades in multi-agent collaboration

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractA single seed can solidify into a false consensus along a fixed collaboration graph.

    The authors turn "small errors becoming collective false consensus" in LLM-MAS into a measurable propagation on a graph, and use a plug-in that only changes messages, not topology, to reduce the final infection.

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end