Skip to content

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

Oct 12 · Monday

All papers

Found 23 papers
Filter3

Attack type

Jailbreaks23Prompt injection24Poisoning and backdoors9Extraction and theft3Detection evasion7Malicious use7

Attack technique

Cross-modal payloads5

Defense type

Monitoring and auditing10

Impact

Harmful content18

System type

Models and APIs18AI Agent4

Attacker access

Black-box8White-box3

Attack surface / entry point

User input17Images, audio and video11

Layer

Prompt layer9Model layer9Application layer5

System component

Memory3Guardrails and judges55Monitors11Reasoning chains14Permissions and sandboxing5Fine-tuning and open weights4Vision32Audio12Image generation15Multimodal58
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：MonitorsSystem component：AudioClear all

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

  1. DefensesarXiv 2610.09167

    Persist-3 用顺序检验识别未见越狱来源，提升 MTK 与 Prompt Guard 2 防御效果

    提出 Persist-3 序贯检验，从隐藏表示识别未见越狱源

    arXiv
    2610.09167
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama2-7B-chat, Qwen2.5-7B-Instruct, Gemma-2-9B-it and others4
    AbstractPersist-3 用有限窗口检验攻击流是否超出已知越狱源，检出率低于全历史 SR-DKW，但决策只依赖最近观测。

    Persist-3 是一个有限记忆的序贯检测器，用来判断攻击表示流是否已经不能由任何一个已知越狱源解释。。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.07005

    研究审计 Qwen2-Audio 音频越狱 AdvWave-P 的频率与解码层归因

    遮挡审计 AdvWave-P 音频越狱的频带必要性与解码层关联

    arXiv
    2610.07005
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2-Audio-7B-Instruct, LLaMA-Omni
    AbstractAdvWave-P 的八频带排序与能量相关。

    这是对加性音频越狱 AdvWave-P 的频率与解码器深度审计，受害模型主要是 Qwen2-Audio-7B-Instruct，不提出新攻击。

    Paper analysisRead analysis
  4. DefensesarXiv 2610.02413

    研究：分类后缀可提升激活探针的分布外恶意输入检测

    用分类后缀提升激活探针对分布外恶意输入的检测

    arXiv
    2610.02413
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Llama-3.1-8B, Qwen3.5-9B, Gemma-4-12B
    Abstract作者称排序增益来自分类格式，低 FPR 精度来自点名准则。

    用户轮后的分类后缀，被作者用作激活探针的分布外检测干预：排序看格式，低 FPR 精度看是否点名恶意/良性。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.30841

    为何扩散语言模型的越狱会成功：能量景观分析

    用能量势垒信号检测扩散语言模型的越狱

    arXiv
    2609.30841
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaDA-8B-Instruct, LLaDA-1.5, Dream-v0-Instruct-7B and others4
    Abstract能量势垒把 dLLM 越狱分成掩盖初始状态或中途越垒，三个 logit 信号据此互补检测。

    Bach 等提出用去噪能量景观解释 masked diffusion 语言模型上的越狱，并由此得到三个免训练检测信号。。

    Paper analysisRead analysis
  11. InterpretabilityarXiv 2609.04721

    研究：拒答方向可跨架构迁移，安全工具可按写入位置重新估计

    在写入点定位拒答方向，经刚性旋转跨架构迁移并门控放大

    arXiv
    2609.04721
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Falcon-Mamba-7B, Falcon3-Mamba-7B, Llama-3.1-8B and others8
    Abstract拒答方向可经刚性旋转跨架构迁移，但必须在各架构的写入点读取。

    作者研究拒答表示是否随架构改变，结论是表示共享、读取位置随架构变。

    Paper analysisRead analysis
  13. Evaluation and benchmarksarXiv 2606.06037

    SpeechJBB：语码转换语音下大型音频语言模型的越狱基准

    提出 SpeechJBB，评测语码转换语音下音频语言模型的越狱稳健性

    arXiv
    2606.06037
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-Omni-7B, Qwen3-Omni-30B-A3B-Instruct, Voxtral-Small-24B and others9
    AbstractSpeechJBB 用五语语码转换语音和伪词探针评测九个 LALM，作者将越狱归为对齐失败而非听不懂。

    SpeechJBB 用合成语音测量 LALM 在五语、语码转换和局部伪词混淆下的安全对齐，并另设口语理解对照。

    Paper analysisRead analysis
  20. AttacksarXiv 2511.10692

    StyleBreak：利用风格化音频越狱揭示大型音频语言模型的对齐漏洞

    提出 StyleBreak 风格化音频越狱，利用语音属性绕过音频语言模型对齐

    arXiv
    2511.10692
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Attacker
    Black-box
    Evaluated models
    Qwen2-Audio-7B-Instruct, MERaLiON-AudioLLM-Whisper-SEA-LION, Ultravox-v0.4.1-Llama-3.1-8B and others6
    Paper analysisRead analysis
Load more