Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 255papers have no tags yet and are not included in filtered results.

Layer：Prompt layer Layer：Training and data layer System component：Memory System component：Audio Clear all

Another 255papers do not have category tags yet and are not included in filtered results.

AttacksarXiv 2610.09819Oct 7
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
arXiv
2610.09819
Published
Oct 7
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
HuBERT-base, WavLM-base
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
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
OtherarXiv 2610.05264Oct 4
面向音频深度伪造检测的任务感知联合剪枝与蒸馏框架
提出任务感知的跨域蒸馏与剪枝方法以压缩音频深度伪造检测器
arXiv
2610.05264
Published
Oct 4
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
XLSR-AASIST
- ComponentAudio
Paper analysisRead analysis
Analysis and theoryarXiv 2610.07005Oct 4
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
Oct 4
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen2-Audio-7B-Instruct, LLaMA-Omni
- AttacksJailbreaks
- ComponentAudio
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
Evaluation and benchmarksarXiv 2609.34092Sep 28
机器遗忘在 ASR 中是否有效：arXiv 论文评估现有算法与评测工具
arXiv
2609.34092
Published
Sep 28
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
E-Branchformer
- DefensesModel hardening
- AttacksExtraction and theft
- ComponentAudio
Abstract梯度上升类方法更接近简单评测下的重训参照，复杂方法会被知情攻击认出，多说话人更差。
Paper analysisRead analysis
DefensesarXiv 2609.12623Sep 11
SteerDuplex：可操控的全双工语音对话模型
提出 SteerDuplex，用监督微调与两阶段强化学习提升全双工语音对话可控性
arXiv
2609.12623
Published
Sep 11
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
SteerDuplex-SFT, SteerDuplex-RL
- DefensesModel hardening
- ComponentAudio
AbstractSteerDuplex 用 SFT 提升语音可控，用两阶段 RL 改时序，并记录奖励黑客。
SteerDuplex 是基于 Moshi 的全双工语音模型，目标是在保留轮替、打断和一般任务能力的同时，按用户指令改变内容与发声。
Paper analysisRead analysis
AttacksarXiv 2609.04260Sep 2
GhostWord：针对自动语音识别的细粒度后门攻击
提出 GhostWord 词级触发后门，对自动语音识别做数据投毒
arXiv
2609.04260
Published
Sep 2
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
Whisper-Small, Whisper-Medium, MMS and others4
- AttacksPoisoning and backdoors
- TechniqueDormant triggers
- ComponentAudio
Paper analysisRead analysis
DefensesarXiv 2608.18607Aug 19
VA-Judger：面向联合视频-音频生成的人类偏好反馈奖励建模
提出 VA-Judger，用人类偏好训练联合音视频奖励模型
arXiv
2608.18607
Published
Aug 19
Layer
Training and data layer
Setting
Models and APIs
Evaluated models
VA-Judger, LTX-2 + VA-Judger
- DefensesModel hardening
- RiskReward hacking
- ComponentGuardrails and judges
AbstractVA-Judger 用易到难的人类偏好学习做联合音视频奖励，并用于 LTX-2 后训练。
VA-Judger 是面向联合音视频生成的思维链全模态奖励模型，用来替代由分维度专家指标拼成的强化学习奖励。
Paper analysisRead analysis
AttacksarXiv 2608.15578Aug 16
ARENA：面向大型音频语言模型的自动化红队框架
提出 ARENA 音频红队框架，自动构造文本安全且音频接地的越狱输入
arXiv
2608.15578
Published
Aug 16
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Audio Flamingo 3, Qwen2-Audio-7B-Instruct, MiMo-Audio-7B-Instruct and others4
- AttacksJailbreaks
- TechniqueAutomated search
- ComponentAudio
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2606.06037Jun 4
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
Jun 4
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
Qwen2.5-Omni-7B, Qwen3-Omni-30B-A3B-Instruct, Voxtral-Small-24B and others9
- AttacksJailbreaks
- TechniqueEncoding and obfuscation
- ComponentAudio
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
AttacksarXiv 2605.20519May 20
CodecAttack：在音频编解码器潜空间构造对抗扰动，绕过有损压缩防御
提出 CodecAttack，在编解码器隐空间构造可穿透有损压缩的对抗音频
arXiv
2605.20519
Published
May 20
Layer
Prompt layer
Setting
Models and APIs
Attacker
White-box
Evaluated models
Qwen2-Audio-7B-Instruct, Audio Flamingo 3, Qwen2.5-Omni
- AttacksJailbreaks
- TechniqueGradient and representation optimization
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2605.18168May 18
研究者提出声学干扰攻击 AIA，可通用越狱 10 个大型音频语言模型
提出声学干扰攻击 AIA，用良性音频潜语义越狱音频语言模型
arXiv
2605.18168
Published
May 18
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen3-Omni, Qwen2.5-Omni, Qwen2-Audio and others10
- AttacksJailbreaks
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2604.14604Apr 16
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
arXiv
2604.14604
Published
Apr 16
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
SpeechGPT, GLM-4-Voice, VITA-Audio and others15
- AttacksPrompt injection
- TechniqueGradient and representation optimization
- ComponentAudio
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
AttacksarXiv 2601.23255Jan 31
研究者提出音频叙事越狱攻击
提出音频叙事越狱，以嗓音投递风格绕过端到端语音模型拒答
arXiv
2601.23255
Published
Jan 31
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
GPT-4o Realtime, Gemini 2.0 Flash, Qwen2.5-Omni-7B
- AttacksJailbreaks
- TechniqueRole-play and persuasion
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2601.16231Jan 21
SoundBreak: A systematic study of pure audio adversarial attacks against trimodal models
提出 SOUNDBREAK，用仅音频共享对抗扰动使三模态模型答错
arXiv
2601.16231
Published
Jan 21
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
VideoLLAMA2, Qwen 2.5 Omni, Qwen 3 Omni and others4
- TechniqueGradient and representation optimization
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2511.10692Nov 12, 2025
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
Nov 12, 2025
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
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2504.01094Apr 2, 2025
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
arXiv
2504.01094
Published
Apr 2, 2025
Layer
Prompt layer
Setting
Models and APIs
Attacker
Black-box
Evaluated models
Qwen2-Audio, DiVA-llama-3-v0-8b, MERaLiON-AudioLLM-Whisper-SEA-LION and others5
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentAudio
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
Evaluation and benchmarksarXiv 2501.13772Jan 23, 2025
Jailbreak-AudioBench：面向大型音频语言模型的越狱评测基准
提出 Jailbreak-AudioBench 评测音频语言模型的音频编辑越狱
arXiv
2501.13772
Published
Jan 23, 2025
Layer
Prompt layer
Setting
Models and APIs
Evaluated models
BLSP, SpeechGPT, Qwen2-Audio-7B and others10
- AttacksJailbreaks
- ComponentAudio
Paper analysisRead analysis

You have reached the end

AI Safety Daily

Read the latest issueOne issue per day, updated as events develop