Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Attack type

Prompt injection5

Defense type

Detection and filtering5

System type

AI Agent6Multi-agent systems3

Attack surface / entry point

User input27Web pages and interfaces7Documents and messages10Tool responses10Tool and skill descriptions10Code repositories and dependencies4Retrieval corpus4Memory writes3Inter-agent messages3Images, audio and video6Distribution channels5

Layer

Application layer7

System component

MCP and skills7Memory7Guardrails and judges7Monitors3Permissions and sandboxing14
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.
Attack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Inter-agent messagesLayer：Application layerSystem component：Guardrails and judgesClear all

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

  1. 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
  2. DefensesarXiv 2608.06422

    CMU 研究：分片判断可避免 LLM 监督失效并抵御对抗利用

    提出分片监督，将评判标准分配给独立调用以抵御展示攻击

    arXiv
    2608.06422
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Opus 4.6 and others4
    Abstract论文揭示决策负载是大模型监督的独立瓶颈，提出分片与辩论机制有效分离注意力与平衡证据，在多项高难度基准上实现稳健评判。

    本文系统研究了大语言模型在执行多标准监督与评判时的决策负载瓶颈及其安全风险。

    Paper analysisRead analysis
  4. DefensesarXiv 2606.08234

    SciTrace：面向科学发现智能体的轨迹感知安全推理框架

    提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验

    arXiv
    2606.08234
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
    AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。

    SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。

    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
  7. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end