Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

Attack type

Jailbreaks4Poisoning and backdoors31Model tampering20Extraction and theft9Detection evasion4

Impact

Harmful content4

System type

Models and APIs3

Attack surface / entry point

User input4

System component

Memory3Guardrails and judges55Monitors11Reasoning chains14Permissions and sandboxing5Fine-tuning and open weights4Vision32Audio12Image generation15Embeddings0Multimodal58
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksSystem component：Fine-tuning and open weightsSystem component：EmbeddingsClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. InterpretabilityarXiv 2609.23587

    大型推理模型的效率与安全困境：量化与剪枝如何影响越狱鲁棒性

    分析量化、剪枝与 KV 缓存压缩对推理模型越狱鲁棒性的影响

    arXiv
    2609.23587
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, DeepSeek-R1-Distill-Llama-8B
    Abstract效率压缩常使 LRM 越狱 HR 下降，作者将其归因于推理退化而非对齐增强。

    作者分析量化、剪枝和 KV 缓存压缩如何同时改变 LRM 的显存、推理和越狱脆弱性。。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2608.08542

    SkillSafe-Bench：技能合并模型静态安全无法预测自适应越狱鲁棒性

    提出 SkillSafe-Bench，评测技能合并模型的自适应越狱鲁棒性

    arXiv
    2608.08542
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Mistral-7B-Instruct-v0.3 and others6
    Abstract论文报告了技能合并大模型在静态安全与自适应越狱间的脱节，提出了评测基准与无数据子空间投影修复方法。

    本研究针对开源语言模型技能合并过程中的安全评估盲区，系统评测并刻画了合并大模型在自适应越狱攻击下的脆弱性特征。

    Paper analysisRead analysis
  3. AttacksarXiv 2601.22169

    In Vino Veritas and Vulnerabilities：用醉酒语言诱导检验 LLM 安全

    用醉酒语言诱导改编对话模型并评测越狱与隐私泄露

    arXiv
    2601.22169
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA2-7B, LLaMA3-8B, Mistral-7B and others5
    Abstract醉酒语言诱导在五个 LLM 上抬高越狱与部分隐私错误，作者将其视为攻击向量。

    作者把醉酒语言当作攻击向量，检验把 LLM 适配成醉酒发短信的模式后，越狱和情境隐私是否变差。动机是人类醉酒时的失范与泄密，以及 LLM 模拟人设的能力。

    Paper analysisRead analysis
You have reached the end