Buchumschlag

Novel Loss-Enhanced Universal Adversarial Patches for Sustainable Speaker Privacy

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Karimov, Elvir, Varlamov, Alexander, Ivanov, Danil, Korzh, Dmitrii, Rogov, Oleg Y.
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Sound Artificial Intelligence Cryptography and Security Audio and Speech Processing
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Certification of Speaker Recognition Models to Additive Perturbations
von: Korzh, Dmitrii, et al.
Veröffentlicht: (2024)

An Effective Energy Mask-based Adversarial Evasion Attacks against Misclassification in Speaker Recognition Systems
von: Park, Chanwoo, et al.
Veröffentlicht: (2026)

A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network
von: Zhao, Haodong, et al.
Veröffentlicht: (2023)

Inference Attacks for X-Vector Speaker Anonymization
von: Bauer, Luke, et al.
Veröffentlicht: (2025)

Quantifying Source Speaker Leakage in One-to-One Voice Conversion
von: Wellington, Scott, et al.
Veröffentlicht: (2025)

Multi-speaker Text-to-speech Training with Speaker Anonymized Data
von: Huang, Wen-Chin, et al.
Veröffentlicht: (2024)

IO-RAE: Information-Obfuscation Reversible Adversarial Example for Audio Privacy Protection
von: Zhu, Jiajie, et al.
Veröffentlicht: (2026)

Privacy in Speech Technology
von: Bäckström, Tom
Veröffentlicht: (2023)

Your Microphone Array Retains Your Identity: A Robust Voice Liveness Detection System for Smart Speakers
von: Meng, Yan, et al.
Veröffentlicht: (2025)

A Practical Survey on Emerging Threats from AI-driven Voice Attacks: How Vulnerable are Commercial Voice Control Systems?
von: Wang, Yuanda, et al.
Veröffentlicht: (2023)

Scenario of Use Scheme: Threat Model Specification for Speaker Privacy Protection in the Medical Domain
von: Rahman, Mehtab Ur, et al.
Veröffentlicht: (2024)

Lightweight Protection for Privacy in Offloaded Speech Understanding
von: Cai, Dongqi
Veröffentlicht: (2024)

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

Adversarial Representation Learning for Robust Privacy Preservation in Audio
von: Gharib, Shayan, et al.
Veröffentlicht: (2023)

Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification
von: Joshi, Sonal, et al.
Veröffentlicht: (2024)

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

Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
von: Luong, Diep, et al.
Veröffentlicht: (2023)

Breaking Speaker Recognition with PaddingBack
von: Ye, Zhe, et al.
Veröffentlicht: (2023)

Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
von: Champion, Pierre
Veröffentlicht: (2023)

Generalizing Speaker Verification for Spoof Awareness in the Embedding Space
von: Liu, Xuechen, et al.
Veröffentlicht: (2024)

EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations
von: Chang, Jung-Woo, et al.
Veröffentlicht: (2024)

DIN-CTS: Low-Complexity Depthwise-Inception Neural Network with Contrastive Training Strategy for Deepfake Speech Detection
von: Pham, Lam, et al.
Veröffentlicht: (2025)

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
von: Borodin, Kirill, et al.
Veröffentlicht: (2024)

VocalCrypt: Novel Active Defense Against Deepfake Voice Based on Masking Effect
von: Fei, Qingyuan, et al.
Veröffentlicht: (2025)

VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents
von: Li, Haiyun, et al.
Veröffentlicht: (2025)

Training Large ASR Encoders with Differential Privacy
von: Chauhan, Geeticka, et al.
Veröffentlicht: (2024)

WaLi: Can Pressure Sensors in HVAC Systems Capture Human Speech?
von: Tamiti, Tarikul Islam, et al.
Veröffentlicht: (2025)

Hybrid Audio Detection Using Fine-Tuned Audio Spectrogram Transformers: A Dataset-Driven Evaluation of Mixed AI-Human Speech
von: Huang, Kunyang, et al.
Veröffentlicht: (2025)

LENS-DF: Deepfake Detection and Temporal Localization for Long-Form Noisy Speech
von: Liu, Xuechen, et al.
Veröffentlicht: (2025)

Cross-Technology Generalization in Synthesized Speech Detection: Evaluating AST Models with Modern Voice Generators
von: Ustinov, Andrew, et al.
Veröffentlicht: (2025)

Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race
von: Mao, Xutao, et al.
Veröffentlicht: (2025)

Why Speech Deepfake Detectors Won't Generalize: The Limits of Detection in an Open World
von: Berisha, Visar, et al.
Veröffentlicht: (2025)

Spoofing attack augmentation: can differently-trained attack models improve generalisation?
von: Ge, Wanying, et al.
Veröffentlicht: (2023)

Sok: Comprehensive Security Overview, Challenges, and Future Directions of Voice-Controlled Systems
von: Xu, Haozhe, et al.
Veröffentlicht: (2024)

Pitch Imperfect: Detecting Audio Deepfakes Through Acoustic Prosodic Analysis
von: Warren, Kevin, et al.
Veröffentlicht: (2025)

Robust AI-Synthesized Speech Detection Using Feature Decomposition Learning and Synthesizer Feature Augmentation
von: Zhang, Kuiyuan, et al.
Veröffentlicht: (2024)

Evaluating Synthetic Command Attacks on Smart Voice Assistants
von: He, Zhengxian, et al.
Veröffentlicht: (2024)

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

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction
von: Ayati, Seyyed Ali, et al.
Veröffentlicht: (2025)

An RFP dataset for Real, Fake, and Partially fake audio detection
von: AlAli, Abdulazeez, et al.
Veröffentlicht: (2024)