Skip to content

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

Oct 13 · Tuesday

All papers

Found 21 papers

Another 201papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2610.09819

    FAB 攻击:给 HuBERT/WavLM 植入后门,背景警笛声即可让下游语音任务失灵

    提出 FAB 攻击,向声学基础模型植入可由环境声触发的后门

    Published
    Evaluated models
    HuBERT-base, WavLM-base

    Abstract论文提出了针对声学基模的 FAB 后门攻击,在弱威胁模型下实现了任务无关、物理可触发的后门植入。

    Paper analysisRead analysis
  2. BabelFake:面向多语言音视频 DeepFake 检测的基准数据集

    构建多语言音视频 DeepFake 基准 BabelFake 并评测检测器

    Published
    Evaluated models
    SpeechForensics, AVH-Align, (B)RAVEn
    AbstractBabelFake 为五语同意采集基准。

    BabelFake 是经同意与 IRB 批准采集的多语音视频 DeepFake 检测基准,用来把视觉操纵和语音合成拆开比较。

    Paper analysisRead analysis
  3. 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

    Published
    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 2609.27399

    GUARD:在 CosyVoice2 上做说话人身份遗忘以阻止重识别

    提出 GUARD,在零样本 TTS 上用激活转向遗忘说话人身份以阻止再识别

    Published
    Evaluated models
    CosyVoice2-0.5B, F5-TTS, FireRedTTS
    AbstractGUARD 用门控激活转向把退出说话人推向冒充相似度,以抑制再识别并保住音质。

    GUARD 用门控激活转向做说话人身份遗忘,使零样本 TTS 对退出说话人难以再识别。

    Paper analysisRead analysis
  5. 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
  6. 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
  7. 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
  8. 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