Imagen de Portada

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Zhisheng, Wang, Derui, Mi, Yifan, Wu, Zhiyong, Gao, Jie, Cao, Yuxin, Ye, Kai, Xue, Minhui, Hao, Jie
Formato:	Preprint
Publicado:	2025
Materias:	Sound Artificial Intelligence Cryptography and Security Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Mirage Fools the Ear, Mute Hides the Truth: Precise Targeted Adversarial Attacks on Polyphonic Sound Event Detection Systems
por: Su, Junjie, et al.
Publicado: (2025)

SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
por: Zhang, Zhisheng, et al.
Publicado: (2025)

Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systems
por: Jin, Weifei, et al.
Publicado: (2025)

ALMGuard: Safety Shortcuts and Where to Find Them as Guardrails for Audio-Language Models
por: Jin, Weifei, et al.
Publicado: (2025)

Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
por: Jin, Weifei, et al.
Publicado: (2024)

Selective Masking Adversarial Attack on Automatic Speech Recognition Systems
por: Fang, Zheng, et al.
Publicado: (2025)

Bones of Contention: Exploring Query-Efficient Attacks against Skeleton Recognition Systems
por: Cao, Yuxin, et al.
Publicado: (2025)

Vulnerabilities of Audio-Based Biometric Authentication Systems Against Deepfake Speech Synthesis
por: Hong, Mengze, et al.
Publicado: (2026)

Boosting the Transferability of Audio Adversarial Examples with Acoustic Representation Optimization
por: Jin, Weifei, et al.
Publicado: (2025)

Adversarial Attacks and Defenses for Speech Recognition Systems
por: Żelasko, Piotr, et al.
Publicado: (2021)

Mitigating Unauthorized Speech Synthesis for Voice Protection
por: Zhang, Zhisheng, et al.
Publicado: (2024)

HVAC-EAR: Eavesdropping Human Speech Using HVAC Systems
por: Tamiti, Tarikul Islam, et al.
Publicado: (2025)

Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
por: Liu, Chang, et al.
Publicado: (2025)

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection
por: Hu, Bin, et al.
Publicado: (2025)

MelShield: Robust Mel-Domain Audio Watermarking for Provenance Attribution of AI Generated Synthesized Speech
por: Jin, Yutong, et al.
Publicado: (2026)

Zero-Query Adversarial Attack on Black-box Automatic Speech Recognition Systems
por: Fang, Zheng, et al.
Publicado: (2024)

Whisper Smarter, not Harder: Adversarial Attack on Partial Suppression
por: Wong, Zheng Jie, et al.
Publicado: (2025)

SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
por: Li, Yue, et al.
Publicado: (2025)

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
por: Chen, Guangke, et al.
Publicado: (2025)

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
por: Cao, Yuxin, et al.
Publicado: (2023)

StyleFool: Fooling Video Classification Systems via Style Transfer
por: Cao, Yuxin, et al.
Publicado: (2022)

Can DeepFake Speech be Reliably Detected?
por: Liu, Hongbin, et al.
Publicado: (2024)

SpeechVerifier: Robust Acoustic Fingerprint against Tampering Attacks via Watermarking
por: Yao, Lingfeng, et al.
Publicado: (2025)

Sirens' Whisper: Inaudible Near-Ultrasonic Jailbreaks of Speech-Driven LLMs
por: Ling, Zijian, et al.
Publicado: (2026)

A Systematic Evaluation of Adversarial Attacks against Speech Emotion Recognition Models
por: Facchinetti, Nicolas, et al.
Publicado: (2024)

SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis
por: Staněk, Vojtěch, et al.
Publicado: (2025)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
por: G, Aravindhan, et al.
Publicado: (2025)

Privacy in Speech Technology
por: Bäckström, Tom
Publicado: (2023)

Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform
por: Zhang, Yichuan, et al.
Publicado: (2025)

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
por: Ba, Zhongjie, et al.
Publicado: (2026)

Where Do Backdoors Live? A Component-Level Analysis of Backdoor Propagation in Speech Language Models
por: Fortier, Alexandrine, et al.
Publicado: (2025)

DUAP: Dual-task Universal Adversarial Perturbations Against Voice Control Systems
por: Sun, Suyang, et al.
Publicado: (2026)

MerkleSpeech: Public-Key Verifiable, Chunk-Localised Speech Provenance via Perceptual Fingerprints and Merkle Commitments
por: Ono, Tatsunori
Publicado: (2026)

Invisible Ears at Your Fingertips: Acoustic Eavesdropping via Mouse Sensors
por: Fakih, Mohamad, et al.
Publicado: (2025)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
por: Roh, Jaechul, et al.
Publicado: (2026)

DECKER: Domain-invariant Embedding for Cross-Keyboard Extraction and Recognition
por: Maurya, Bikrant Bikram Pratap, et al.
Publicado: (2026)

Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
por: Yao, Lingfeng, et al.
Publicado: (2026)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
por: Wang, Yanyun, et al.
Publicado: (2026)

ClearMask: Noise-Free and Naturalness-Preserving Protection Against Voice Deepfake Attacks
por: Wang, Yuanda, et al.
Publicado: (2025)

DASM: Domain-Aware Sharpness Minimization for Multi-Domain Voice Stream Steganalysis
por: Zhou, Pengcheng, et al.
Publicado: (2026)