cs.CR

Papers

• Trading Devil: Robust backdoor attack via Stochastic investment models and Bayesian approach (2025)
  Orson Mengara
  4.52
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking (2026)
  Wenyuan Yang et al.
  0.00
• Red-Teaming Claude Opus and ChatGPT-based Security Advisors for Trusted Execution Environments (2026)
  Kunal Mukherjee et al.
  0.00
• Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs (2026)
  Ziyang Liu
  0.00
• SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud (2021)
  Zahra Ghodsi et al.
  —
• The Audio Auditor: User-Level Membership Inference in Internet of Things Voice Services (2021)
  Yuantian Miao et al.
  —
• VoIPLoc: Passive VoIP call provenance via acoustic side-channels (2021)
  Shishir Nagaraja et al.
  —
• Short-Range Audio Channels Security: Survey of Mechanisms, Applications, and Research Challenges (2022)
  Maurantonio Caprolu et al.
  —
• Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement (2022)
  Chao-Han Huck Yang et al.
  —
• Acoustic Integrity Codes: Secure Device Pairing Using Short-Range Acoustic Communication (2023)
  Florentin Putz et al.
  —
• Private Speech Classification with Secure Multiparty Computation (2021)
  Kyle Bittner et al.
  —
• VenoMave: Targeted Poisoning Against Speech Recognition (2023)
  Hojjat Aghakhani et al.
  —
• Backdoor Attack against Speaker Verification (2021)
  Tongqing Zhai et al.
  —
• Stop Bugging Me! Evading Modern-Day Wiretapping Using Adversarial Perturbations (2021)
  Yael Mathov and Tal Ben Senior and Asaf Shabtai and Yuval Elovici
  —
• Speaker Anonymization with Distribution-Preserving X-Vector Generation for the VoicePrivacy Challenge 2020 (2021)
  Henry Turner et al.
  —
• Adversarial Disentanglement of Speaker Representation for Attribute-Driven Privacy Preservation (2021)
  Paul-Gauthier No\'e et al.
  —
• Practical Speech Re-use Prevention in Voice-driven Services (2021)
  Yangyong Zhang et al.
  —
• A Study of F0 Modification for X-Vector Based Speech Pseudonymization Across Gender (2021)
  Pierre Champion (MULTISPEECH) et al.
  —
• Understanding the Tradeoffs in Client-side Privacy for Downstream Speech Tasks (2021)
  Peter Wu et al.
  —
• Adversarial Attacks and Defenses for Speech Recognition Systems (2024)
  Piotr \.Zelasko et al.
  —
• Can You Hear It? Backdoor Attacks via Ultrasonic Triggers (2023)
  Stefanos Koffas et al.
  —
• Improving Speaker Identification for Shared Devices by Adapting Embeddings to Speaker Subsets (2022)
  Zhenning Tan and Yuguang Yang and Eunjung Han and Andreas Stolcke
  —
• Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement (2023)
  Xavier Gitiaux et al.
  —
• Estimating the confidence of speech spoofing countermeasure (2022)
  Xin Wang et al.
  —
• Source Mixing and Separation Robust Audio Steganography (2022)
  Naoya Takahashi et al.
  —
• Speech Pattern based Black-box Model Watermarking for Automatic Speech Recognition (2022)
  Haozhe Chen et al.
  —
• Privacy attacks for automatic speech recognition acoustic models in a federated learning framework (2022)
  Natalia Tomashenko et al.
  —
• RawBoost: A Raw Data Boosting and Augmentation Method applied to Automatic Speaker Verification Anti-Spoofing (2022)
  Hemlata Tak et al.
  —
• Membership Inference Attacks Against Self-supervised Speech Models (2022)
  Wei-Cheng Tseng et al.
  —
• Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings (2022)
  Tiantian Feng and Hanieh Hashemi and Rajat Hebbar and Murali Annavaram and Shrikanth S. Narayanan
  —
• A Practical Guide to Logical Access Voice Presentation Attack Detection (2022)
  Xin Wang and Junichi Yamagishi
  —
• Synthetic speech detection using meta-learning with prototypical loss (2022)
  Monisankha Pal et al.
  —
• Optimizing Tandem Speaker Verification and Anti-Spoofing Systems (2022)
  Anssi Kanervisto et al.
  —
• SASV Challenge 2022: A Spoofing Aware Speaker Verification Challenge Evaluation Plan (2022)
  Jee-weon Jung et al.
  —
• Language Dependencies in Adversarial Attacks on Speech Recognition Systems (2022)
  Karla Markert and Donika Mirdita and Konstantin B\"ottinger
  —
• Tubes Among Us: Analog Attack on Automatic Speaker Identification (2023)
  Shimaa Ahmed et al.
  —
• FAAG: Fast Adversarial Audio Generation through Interactive Attack Optimisation (2022)
  Yuantian Miao et al.
  —
• On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systems (2023)
  Zesheng Chen
  —
• Attributable-Watermarking of Speech Generative Models (2022)
  Yongbaek Cho et al.
  —
• Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey (2022)
  Ngoc Dung Huynh et al.
  —
• Differentially Private Speaker Anonymization (2022)
  Ali Shahin Shamsabadi et al.
  —
• Speech watermarking: an approach for the forensic analysis of digital telephonic recordings (2022)
  Marcos Faundez-Zanuy et al.
  —
• aaeCAPTCHA: The Design and Implementation of Audio Adversarial CAPTCHA (2022)
  Md Imran Hossen and Xiali Hei
  —
• Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems (2022)
  Hadi Abdullah et al.
  —
• Semi-FedSER: Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling (2023)
  Tiantian Feng and Shrikanth Narayanan
  —
• Privacy-Preserving Speech Representation Learning using Vector Quantization (2022)
  Pierre Champion (MULTISPEECH) et al.
  —
• A combination between VQ and covariance matrices for speaker recognition (2022)
  Marcos Faundez-Zanuy
  —
• The VoicePrivacy 2022 Challenge Evaluation Plan (2022)
  Natalia Tomashenko et al.
  —
• WaveFuzz: A Clean-Label Poisoning Attack to Protect Your Voice (2022)
  Yunjie Ge et al.
  —
• A Speech Representation Anonymization Framework via Selective Noise Perturbation (2022)
  Minh Tran et al.
  —