Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Attack type

Jailbreaks3

System type

Models and APIs4

Attack surface / entry point

User input192Web pages and interfaces0Tool responses3Images, audio and video75Training data4Weights and gradients1

Layer

Prompt layer4Model layer30Application layer157Training and data layer37
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.
Attack surface / entry point：Web pages and interfacesAttack surface / entry point：Tool responsesAttack surface / entry point：Weights and gradientsLayer：Prompt layerClear all

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

  1. 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
  2. AttacksarXiv 2608.07430

    研究者提出 SN-Guided Diffusion，利用扩散大模型安全神经元实现离线越狱

    提出 SN-Guided Diffusion，利用安全神经元实现离线越狱

    arXiv
    2608.07430
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Qwen2.5-7B-Instruct, LLaDA-8B-Instruct, Dream-Instruct-7B and others15
    Abstract论文揭示了扩散语言模型对自回归安全神经元的继承性，并提出纯离线黑盒越狱框架 SN-Guided Diffusion。

    论文系统评估了扩散大语言模型（DLLM）在安全对齐中的双重角色——既作为白盒攻击目标，又作为黑盒越狱生成的对抗工具。

    Paper analysisRead analysis
  4. AttacksarXiv 2606.06244

    研究者提出 Ghostwriter 攻击：用伪造证据注入操纵 LLM 观点

    提出 Ghostwriter 攻击，用伪权威证据条件注入操纵模型观点

    arXiv
    2606.06244
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    GPT-4o, Claude-3.7-Sonnet, DeepSeek-V3 and others10
    Abstract作者称攻击未被消除。

    Ghostwriter 是一种针对上下文窗口的观点引导攻击：把误导陈述改写成伪权威文本，再在相关查询中让目标模型把该观点写进回答。

    Paper analysisRead analysis
You have reached the end