Skip to content

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

Oct 12 · Monday

All papers

Found 11 papers

Another 232papers do not have category tags yet and are not included in filtered results.

  1. MMPIBench:多模态提示注入对六种 Agent 框架的跨框架评测

    用 MMPIBench 评测多模态提示注入对 Agent 框架的影响

    Published
    Setting
    AI Agent
    Evaluated models
    Claude Opus 4.8, GPT-5.4, Gemini 3.1 Pro and others6

    Abstract论文提出 MMPIBench 评测多模态提示注入对智能体的影响,发现模型主导行为、尝试远超完成,音频通道缺乏防护。

    Paper analysisRead analysis
  2. AttacksarXiv 2606.12716

    PaperGuard:针对多模态 AI 同行评审的攻击与防御基准

    提出 PaperGuard,用图文注入与梯度扰动抬高自动审稿分数并检测恶意指令

    Published
    Evaluated models
    Claude-sonnet-4.5, GPT-4o, GPT-4.1 and others11
    AbstractPaperGuard 测到提示注入与白盒视觉抬分,并比较分块检索防御。

    PaperGuard同时评测并检测多模态 AI 审稿中的评分操纵。

    Paper analysisRead analysis
  3. AttacksarXiv 2606.09084

    研究者提出 Context-Fractured Decomposition 攻击

    提出 CFD 跨会话分解攻击,利用工件来源缺口绕过工具型 Agent 的本地检查

    Published
    Setting
    AI Agent
    Evaluated models
    GPT-4.1, GPT-5-nano, Claude-3.5-Sonnet and others6
    AbstractCFD 用无指令 artifact 把越狱拆到跨会话。

    CFD针对工具型 LLM 智能体:利用 artifact 来源不被跟踪这一部署失败模式,把有害目标拆开后延迟组合。

    Paper analysisRead analysis
  4. AttacksarXiv 2604.14604

    The AudioHijack framework achieves covert audio prompt injection against 13 speech large models

    提出 AudioHijack,用不可感知对抗音频对语音模型做上下文无关提示注入

    Published
    Evaluated models
    SpeechGPT, GLM-4-Voice, VITA-Audio and others15

    Abstract提出了 AudioHijack 框架,揭示了 LALM 对听觉提示注入的脆弱性与传统防御的局限。

    Paper analysisRead analysis
  5. 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

    Published
    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
  6. AttacksarXiv 2504.01094

    研究者提出 Multi-AudioJail

    提出 MULTI-AUDIOJAIL,以多语多口音和声学扰动越狱音频模型

    Published
    Attacker
    Black-box
    Evaluated models
    Qwen2-Audio, DiVA-llama-3-v0-8b, MERaLiON-AudioLLM-Whisper-SEA-LION and others5

    Abstract黑盒多语多口音音频加声学扰动可抬高 LALM 的 JSR,文本示范防御并非在每个模型上都下降。

    Paper analysisRead analysis
You have reached the end