Image de couverture de livre

StyleBreak: Revealing Alignment Vulnerabilities in Large Audio-Language Models via Style-Aware Audio Jailbreak

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Li, Hongyi, Zhou, Chengxuan, Wang, Chu, Liang, Sicheng, Chen, Yanting, Xie, Qinlin, Ye, Jiawei, Wu, Jie
Format:	Preprint
Publié:	2025
Sujets:	Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Content and Style Aware Audio-Driven Facial Animation
par: Liu, Qingju, et autres
Publié: (2024)

Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation
par: Feng, Bo-Han, et autres
Publié: (2026)

Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models
par: Song, Zirui, et autres
Publié: (2025)

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
par: Peng, Zifan, et autres
Publié: (2025)

Neural Style Transfer for Audio Spectograms
par: Verma, Prateek, et autres
Publié: (2018)

Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
par: Jin, Weifei, et autres
Publié: (2024)

ChronosAudio: A Comprehensive Long-Audio Benchmark for Evaluating Audio-Large Language Models
par: Luo, Kaiwen, et autres
Publié: (2026)

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
par: Chen, Guangke, et autres
Publié: (2025)

Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models
par: Cheng, Hao, et autres
Publié: (2025)

ERIS: Evolutionary Real-world Interference Scheme for Jailbreaking Audio Large Models
par: Zhang, Yibo, et autres
Publié: (2025)

Resonate: Reinforcing Text-to-Audio Generation via Online Feedback from Large Audio Language Models
par: Li, Xiquan, et autres
Publié: (2026)

RA-CLAP: Relation-Augmented Emotional Speaking Style Contrastive Language-Audio Pretraining For Speech Retrieval
par: Sun, Haoqin, et autres
Publié: (2025)

Serenade: A Singing Style Conversion Framework Based On Audio Infilling
par: Violeta, Lester Phillip, et autres
Publié: (2025)

GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
par: Wang, Yunqiang, et autres
Publié: (2026)

Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
par: Wu, Daiqing, et autres
Publié: (2026)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
par: Roh, Jaechul, et autres
Publié: (2026)

HybridVC: Efficient Voice Style Conversion with Text and Audio Prompts
par: Niu, Xinlei, et autres
Publié: (2024)

ST-ITO: Controlling Audio Effects for Style Transfer with Inference-Time Optimization
par: Steinmetz, Christian J., et autres
Publié: (2024)

AudioRAG+: Feedback-driven Retrieval-augmented Audio Generation with Large Audio Language Models
par: Zhao, Junqi, et autres
Publié: (2025)

MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model
par: Tao, Ye, et autres
Publié: (2025)

Audio Hallucination Attacks: Probing the Reliability of Large Audio Language Models
par: Seth, Ashish, et autres
Publié: (2026)

SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
par: Zhu, Yi, et autres
Publié: (2024)

Scaling Audio-Text Retrieval with Multimodal Large Language Models
par: Xu, Jilan, et autres
Publié: (2026)

AudioKV: KV Cache Eviction in Efficient Large Audio Language Models
par: Wang, Yuxuan, et autres
Publié: (2026)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
par: Wang, Yanyun, et autres
Publié: (2026)

TalkingMachines: Real-Time Audio-Driven FaceTime-Style Video via Autoregressive Diffusion Models
par: Low, Chetwin, et autres
Publié: (2025)

Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation
par: Xiong, Chenxu, et autres
Publié: (2024)

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models
par: Gupta, Isha, et autres
Publié: (2025)

Precise and Simple Audio-to-Score Alignment
par: Peter, Silvan, et autres
Publié: (2026)

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack
par: Ziv, Roee, et autres
Publié: (2025)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
par: Fang, Zheng, et autres
Publié: (2026)

Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learning
par: Xie, Yuankun, et autres
Publié: (2026)

Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
par: Kim, Nam-Gyu
Publié: (2025)

Causal Tracing of Audio-Text Fusion in Large Audio Language Models
par: Chen, Wei-Chih, et autres
Publié: (2026)

OWL: Geometry-Aware Spatial Reasoning for Audio Large Language Models
par: Biswas, Subrata, et autres
Publié: (2025)

Unlocking Large Audio-Language Models for Interactive Language Learning
par: Liu, Hongfu, et autres
Publié: (2026)

SpotSound: Enhancing Large Audio-Language Models with Fine-Grained Temporal Grounding
par: Sun, Luoyi, et autres
Publié: (2026)

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
par: Dinkel, Heinrich, et autres
Publié: (2026)

Beyond Transcription: Unified Audio Schema for Perception-Aware AudioLLMs
par: Zhang, Linhao, et autres
Publié: (2026)

Spotlight-TTS: Spotlighting the Style via Voiced-Aware Style Extraction and Style Direction Adjustment for Expressive Text-to-Speech
par: Kim, Nam-Gyu, et autres
Publié: (2025)