Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.

Layer：Prompt layer Layer：Application layer System component：Audio Clear all

Another 254papers do not have category tags yet and are not included in filtered results.

Evaluation and benchmarksarXiv 2610.08585Oct 6
研究：无关信息污染患者病历并干扰 LLM 临床推理
构建 MedDistract 基准，测量偶发信息对临床文书与推理的污染
arXiv
2610.08585
Published
Oct 6
Layer
Application layer
Setting
LLM applications
Evaluated models
GPT-5.4, GPT-5.6 Sol, Claude Opus 5 and others9
- RiskHallucination and fabrication
- 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
DefensesarXiv 2610.01184Oct 1
ReCast：在固定媒体接口下保护多模态推理的隐私框架
提出 RECAST，本地改写图表与语音并做可逆数值映射以保护远程推理隐私
arXiv
2610.01184
Published
Oct 1
Layer
Application layer
Setting
LLM applications
- ComponentVision
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.35922Sep 28
VoxParity 评测：语音智能体在需要听声判断时仍按文字行事
提出 VoxParity，固定转写只改音频，评测语音智能体是否按行业规则改工具调用
arXiv
2609.35922
Published
Sep 28
Layer
Application layer
Setting
AI Agent
Evaluated models
MiMo-V2.6-Pro, gemini-3.7-flash, Qwen3.8-Omni and others15
- RiskDangerous agent actions
- ComponentAudio
AbstractVoxParity 用固定转写的音频对比和 words-only null，测量语音智能体是否按所听内容改变工具调用。
VoxParity 测量语音智能体在词语不变、只有声音改变时，是否按行业规则改它所执行的工具调用。
Paper analysisRead analysis
Evaluation and benchmarksarXiv 2609.09404Sep 9
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
arXiv
2609.09404
Published
Sep 9
Layer
Application layer
Setting
AI Agent
Evaluated models
Claude Opus 4.8, GPT-5.4, Gemini 3.1 Pro and others6
- AttacksPrompt injection
- TechniqueCross-modal payloads
- ComponentVision
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
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 2603.13847Mar 14
SWhisper 用近超声隐蔽声学通道对语音驱动 LLM 实现黑盒越狱
提出 SWhisper，用近超声波向语音驱动 LLM 隐蔽注入越狱提示
arXiv
2603.13847
Published
Mar 14
Layer
Application layer
Setting
LLM applications
Attacker
Black-box
Evaluated models
Meta-Llama-3.1-8B-Instruct, Gemma-3-4B, Qwen2.5-7B-Instruct and others9
- AttacksJailbreaks
- TechniqueCross-modal payloads
- ComponentAudio
Paper analysisRead analysis
AttacksarXiv 2602.07379Feb 7
Aegis: Governance, Integrity, and Security for AI Voice Agents
提出 Aegis 红队框架，多轮攻击高风险语音 Agent
arXiv
2602.07379
Published
Feb 7
Layer
Application layer
Setting
AI Agent
Evaluated models
GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
- AttacksDenial of service
- TechniqueMulti-turn escalation
- ComponentAudio
AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.
Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.
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