Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter2

Attack type

Prompt injection4

Defense type

Detection and filtering3

Impact

Output manipulation3

System type

LLM applications4

Attack surface / entry point

User input74Web pages and interfaces7Documents and messages10Tool responses12Tool and skill descriptions9Code repositories and dependencies4Retrieval corpus4Memory writes3Inter-agent messages3Images, audio and video19Training data3Distribution channels6

Layer

Application layer4

System component

Memory4RAG23Guardrails and judges4Permissions and sandboxing4Embeddings6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Retrieval corpusSystem component：Guardrails and judgesClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  3. 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
  4. 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
You have reached the end