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 optimization4Automated search27Multi-turn escalation4Encoding and obfuscation23Role-play and persuasion6Conversation structure manipulation2Reasoning-chain manipulation4Cross-modal payloads9Defense-targeted19Dormant triggers29

System component

Memory0Guardrails and judges2Reasoning chains4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Attack technique：Conversation structure manipulationSystem component：MemorySystem component：Guardrails and judgesClear all

Another 213papers 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 2510.10271

    MetaBreak：通过特殊 token 操纵越狱在线 LLM 服务

    提出 MetaBreak，用特殊 token 操纵越狱在线 LLM 服务并绕过审核

    arXiv
    2510.10271
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Llama-3.3-70B-Instruct, Qwen-2.5-72B-Instruct, Gemma-2-27B-Instruct and others10

    Abstract利用特殊 token 注入对抗平台模板包裹与审核，多场景验证了越狱有效性与互补性。

    Paper analysisRead analysis
You have reached the end