Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Model risks

Deception and scheming3Misalignment and value divergence4Dangerous agent actions7

Attack surface / entry point

User input5Tool responses2Code repositories and dependencies0Training data1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Model risks：Deception and schemingAttack surface / entry point：Tool responsesAttack surface / entry point：Code repositories and dependenciesAttack surface / entry point：Training dataClear all

Another 232papers 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
  2. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2609.29429

    Jev 被用于零样本检测十类对齐失败，中位 AUROC 达 0.886

    提出 RLCDAlignBench，零样本检测多种对齐失败

    arXiv
    2609.29429
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Jev (jev-1.13.0)
    Abstract一次通用问题已能给多数对齐失败排序，大的误差来自状态和标签。

    RLCDAlignBench 测量用强化学习做校准决策的 Jev，能否当作对齐失败的零样本检测器。

    Paper analysisRead analysis
You have reached the end