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

Jailbreaks4Poisoning and backdoors7Detection evasion13

Impact

Harmful content32Output manipulation3Availability and reliability1

System type

Models and APIs4

Attack surface / entry point

User input3

Layer

Prompt layer4Model layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksImpact：Output manipulationImpact：Availability and reliabilityLayer：Model layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.10276

    PatchBench 提出激活补丁局部评测协议，揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议，评测激活补丁修复越狱的局部附带损伤

    arXiv
    2610.10276
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议，揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2609.36477

    研究发现护栏模型在基座模型不确定处过度自信

    诊断护栏相对基座在对抗提示上的置信失校

    arXiv
    2609.36477
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-Guard 7B, Llama-Guard-2 8B, Llama-Guard-3 8B and others10
    Abstract对抗包装使 guard 高置信漏检，而对应 base 在同一输入上常更不确定。

    诊断性分析：五个提示词分类 guard 的置信度，在清洁输入上可以较校准，在越狱包装后则变成高置信度的错误判定。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2602.19450

    对面向可信执行环境的 Claude Opus 与 ChatGPT 安全顾问进行红队测试

    用 TEE-REDBENCH 评测 TEE 顾问的机制幻觉与提示诱导失败

    arXiv
    2602.19450
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    ChatGPT-5.2, Claude Opus-4.6
    Abstract作者用 TEE-REDBENCH 测两款顾问，称失败可迁移且流水线控制可降低发生率。

    TEE-REDBENCH 红队评测被当作 Intel SGX 与 Arm TrustZone 安全顾问的 ChatGPT-5.2 和 Claude Opus-4.6，看架构推理、远程证明语义、缓解建议和策略约束下的拒答，并测提示诱导失败能否跨助手迁移。作者把助手看成随机策略。

    Paper analysisRead analysis
You have reached the end