Buchumschlag

Selective Masking Adversarial Attack on Automatic Speech Recognition Systems

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Fang, Zheng, Zhang, Shenyi, Wang, Tao, Li, Bowen, Zhao, Lingchen, Wang, Zhangyi
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Cryptography and Security Sound
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

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

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

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

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

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

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

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

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

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
von: Fang, Zheng, et al.
Veröffentlicht: (2026)

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

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

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

Hijacking Attacks against Neural Networks by Analyzing Training Data
von: Ge, Yunjie, et al.
Veröffentlicht: (2024)

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

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
von: Cheng, Peng, et al.
Veröffentlicht: (2024)

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation
von: Zhang, Shenyi, et al.
Veröffentlicht: (2025)

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

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

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

SyncGuard: Robust Audio Watermarking Capable of Countering Desynchronization Attacks
von: Gan, Zhenliang, et al.
Veröffentlicht: (2025)

STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
von: Wang, Kun, et al.
Veröffentlicht: (2026)

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

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

Exploratory Evaluation of Speech Content Masking
von: Williams, Jennifer, et al.
Veröffentlicht: (2024)

Frame-level Temporal Difference Learning for Partial Deepfake Speech Detection
von: Li, Menglu, et al.
Veröffentlicht: (2025)

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

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis
von: Zhang, Zhisheng, et al.
Veröffentlicht: (2025)

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

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

Amulet: Fast TEE-Shielded Inference for On-Device Model Protection
von: Mao, Zikai, et al.
Veröffentlicht: (2025)

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

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

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)

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

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

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
von: Kang, Mintong, et al.
Veröffentlicht: (2024)

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

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack
von: Ziv, Roee, et al.
Veröffentlicht: (2025)

SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
von: Lin, Weilin, et al.
Veröffentlicht: (2025)

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