Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

Attack technique

Gradient and representation optimization8Automated search14Encoding and obfuscation5Conversation structure manipulation2Cross-modal payloads5Dormant triggers8Selection manipulation3

Attack surface / entry point

User input13Web pages and interfaces1Retrieval corpus1
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.
Attack technique：Conversation structure manipulationAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Retrieval corpusClear all

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

  1. 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
  2. AttacksarXiv 2605.24421

    研究者提出日志型提示注入攻击，可抑制 SOC 中 LLM 分析助手的恶意日志识别

    提出日志基底提示注入，操纵 SOC 分析员的分类、摘要与处置建议

    arXiv
    2605.24421
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    gpt-4o-mini

    Abstract在 gpt-4o-mini 上，人格劫持与上下文操纵可改写 SOC 分析输出，直接覆盖在分类上无效。

    Paper analysisRead analysis
You have reached the end