Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Attack type

Jailbreaks45Extraction and theft2Detection evasion4

Attack technique

Automated search4Encoding and obfuscation1Conversation structure manipulation1Side channels3

System type

Models and APIs2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack technique：Encoding and obfuscationAttack technique：Conversation structure manipulationSystem type：Models and APIsClear all

Another 255papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2608.09867

    Researchers steal proprietary LLM inference chains via cross-model compatibility of encrypted inference blocks

    利用加密思维块的跨模型重放，诱导弱模型逐字转写专有推理链

    arXiv
    2608.09867
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Claude Opus 4.8, Claude Sonnet 4.6, Claude Haiku 4.5 and others13

    Abstract论文揭示了客户端加密思维块跨模型互换漏洞，提出了低成本提取方法并给出防御方案。

    Paper analysisRead analysis
  2. AttacksarXiv 2604.01039

    Evaluating and hardening LLM system instructions against encoding attack extraction

    Extract system instructions with encoding and structured requests, and harden them by rewriting with CoT

    arXiv
    2604.01039
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    GPT-4.1-mini, GPT-3.5-turbo, Gemini-2.5-flash and others7
    AbstractEncoded requests can elicit system instructions after a direct refusal.

    This work evaluates and hardens the confidentiality of LLM system instructions under encoded extraction. The authors are concerned with: when direct extraction has been rejected, whether the model still surrenders protected content when the same request is rewritten as a formatting or encoding task.

    Paper analysisRead analysis
You have reached the end