Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

System type

Models and APIs3AI Agent3

Attack surface / entry point

User input24Documents and messages0Code repositories and dependencies1Images, audio and video5Training data3Weights and gradients2

System component

Reasoning chains3Fine-tuning and open weights29Image generation6Multimodal9
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
System type：Models and APIsAttack surface / entry point：Documents and messagesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Weights and gradientsSystem component：Reasoning chainsClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.38909

    Purdue 提出 Pact：将欺骗作为行为遗忘

    提出 PACT，遗忘推理模型在压力下的欺骗行为并保留上下文理解

    arXiv
    2609.38909
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    DeepSeek-R1-Distill-Qwen-32B, QwQ-32B

    Abstract论文将大模型欺骗形式化为上下文条件行为，提出 PACT 框架在消除欺骗的同时保留了上下文遵循能力。

    Paper analysisRead analysis
  3. 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
You have reached the end