Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter3

Attack type

Jailbreaks4Poisoning and backdoors28Model tampering20Extraction and theft4Detection evasion3

Attack technique

Defense-targeted3

Impact

Harmful content4

System type

Models and APIs5

Attack surface / entry point

User input5Weights and gradients3

System component

MCP and skills6Memory3RAG5Guardrails and judges75Monitors16Reasoning chains18Permissions and sandboxing6Fine-tuning and open weights7Vision41Audio14Video4Image generation22Multimodal77
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：JailbreaksAttack type：Detection evasionSystem component：Fine-tuning and open weightsClear all

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

  1. AttacksarXiv 2610.03124

    研究提出 Untag 攻击框架，使开源大模型触发标签滥用检测机制失效

    提出 UNTAG，绕过开源权重模型的 trigger-tag 滥用检测

    arXiv
    2610.03124
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Attacker
    Black-box, White-box
    Evaluated models
    Llama2 (7B), Llama3 (8B), Qwen2.5 (7B)
    Abstract作者用 UNTAG 评估 trigger-tag，认为其不能充当开放权重滥用检测的主要边界。

    UNTAG 是针对开放权重 LLM 上条件滥用检测 trigger-tag 的统一攻击评估：信号可以在解码期注入，也可以写进权重，但攻击者若能改输出或改已发布权重，检测可以失效。

    Paper analysisRead analysis
  2. AttacksarXiv 2609.37468

    论文提出针对 Agentic RAG 的检索器后门攻击与 DOU 隐藏方法

    提出检索器后门攻击操纵智能体搜索，并用 DOU 逃避检测

    arXiv
    2609.37468
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    E5, Contriever-MSMARCO

    Abstract论文展示了通过恶意检索器操纵智能体多轮搜索并利用诱饵重塑表征隐蔽后门的可行性与系统风险。

    Paper analysisRead analysis
  3. 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
  4. 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
  5. 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
  6. AttacksarXiv 2601.14310

    CORVUS：用 LoRA 伪装内部信号绕过单次幻觉检测器

    提出 CORVUS，用 LoRA 伪装内部遥测以绕过幻觉检测器

    arXiv
    2601.14310
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box
    Evaluated models
    Llama-2-7B-Chat, Vicuna-7B (v1.5), Llama-3-8B-Instruct and others4

    Abstract作者称内部遥测在自适应模型侧对抗下易被操纵，CORVUS 通过轻量适配器微调降低了多种幻觉检测器的效果。

    Paper analysisRead analysis
You have reached the end