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 injection5Poisoning and backdoors4

Impact

Unauthorized actions3

System type

Models and APIs3LLM applications23AI Agent47coding agent4Multi-agent systems8

Attack surface / entry point

User input298Web pages and interfaces3Documents and messages13Tool responses11Tool and skill descriptions25Code repositories and dependencies20Retrieval corpus3Memory writes4Images, audio and video99Training data65Weights and gradients64Distribution channels34Inference services and hardware17

Layer

Application layer4

System component

Memory3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentAttack surface / entry point：Retrieval corpusAttack surface / entry point：Memory writesClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2609.37737

    研究用因果激活修补定位模型服从提示注入指令的决策层

    用因果激活修补定位模型服从提示注入的决策层

    arXiv
    2609.37737
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen3-4B, Qwen3-14B, Qwen3-32B and others7
    Abstract合规的因果杠杆集中在网络后三分之一的低秩子空间，该层也是混淆下检测最好的位置。

    这篇工作用逐层激活修补定位提示注入合规发生在网络何处，并把该位置用于检测验证。。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2607.14611

    论文评测 Claude Code 与 Codex 记忆文件中的提示注入风险

    评测编码 Agent 记忆文件中提示注入的跨会话影响

    arXiv
    2607.14611
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Haiku 4.5, Claude Opus 4.7, GPT-5.2 and others4
    Abstract已植入记忆文件的载荷可以跨会话影响 Claude Code 与 Codex，攻击成功与载荷是否留下是两种不同的失败。

    Bad Memory 在沙箱合成工作区里评测文件型持久记忆上的提示注入，比较载荷能否改变当前会话，以及能否在后续会话中留下或叠加。

    Paper analysisRead analysis
  6. AttacksarXiv 2606.06244

    研究者提出 Ghostwriter 攻击：用伪造证据注入操纵 LLM 观点

    提出 Ghostwriter 攻击，用伪权威证据条件注入操纵模型观点

    arXiv
    2606.06244
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude-3.7-Sonnet, DeepSeek-V3 and others10
    Abstract作者称攻击未被消除。

    Ghostwriter 是一种针对上下文窗口的观点引导攻击：把误导陈述改写成伪权威文本，再在相关查询中让目标模型把该观点写进回答。

    Paper analysisRead analysis
  7. AttacksarXiv 2602.01757

    Zero2Text: Training-Free Cross-Domain Text Embedding Inversion Attack

    提出 Zero2Text，无需训练地跨域反演文本嵌入

    arXiv
    2602.01757
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GTR-Base, Qwen3-Embedding-0.6B, Text-Embedding-3-small and others4
    Abstract零训练在线对齐可在未知域、无泄漏对时从黑盒 embedding 还原句子。

    Zero2Text 是一种不训练 decoder、也不使用泄漏文本–向量对的文本 embedding 反演，针对 RAG 向量库在严格黑盒、目标域未知时的还原。

    Paper analysisRead analysis
You have reached the end