{"total":113,"rows":[{"id":"2408.08739","title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","created":"2024-08-16","cited_by_count":91,"area":null},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2401.17264","title":"Proactive Detection of Voice Cloning with Localized Watermarking","created":"2024-01-30","cited_by_count":78,"area":null},{"id":"2503.02857","title":"Deepfake-Eval-2024: A Multi-Modal In-the-Wild Benchmark of Deepfakes Circulated in 2024","created":"2025-03-04","cited_by_count":45,"area":null},{"id":"2405.04880","title":"The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio","created":"2024-05-08","cited_by_count":31,"area":null},{"id":"2306.01428","title":"Improved DeepFake Detection Using Whisper Features","created":"2023-06-02","cited_by_count":29,"area":null},{"id":"2406.17376","title":"Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detection","created":"2024-06-25","cited_by_count":25,"area":null},{"id":"2403.13335","title":"Adaptive Ensembles of Fine-Tuned Transformers for LLM-Generated Text Detection","created":"2024-03-20","cited_by_count":22,"area":null},{"id":"2309.07525","title":"SingFake: Singing Voice Deepfake Detection","created":"2023-09-14","cited_by_count":21,"area":null},{"id":"2509.02859","title":"Speech DF Arena: A Leaderboard for Speech DeepFake Detection Models","created":"2025-09-02","cited_by_count":21,"area":null},{"id":"2211.02718","title":"SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing","created":"2022-11-04","cited_by_count":18,"area":null},{"id":"2411.00121","title":"I Can Hear You: Selective Robust Training for Deepfake Audio Detection","created":"2024-10-31","cited_by_count":13,"area":null},{"id":"2309.02232","title":"FSD: An Initial Chinese Dataset for Fake Song Detection","created":"2023-09-05","cited_by_count":12,"area":null},{"id":"2410.04324","title":"Where are we in audio deepfake detection? A systematic analysis over generative and detection models","created":"2024-10-06","cited_by_count":11,"area":null},{"id":"2406.02483","title":"How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio?","created":"2024-06-04","cited_by_count":10,"area":null},{"id":"2305.14097","title":"QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems","created":"2023-05-23","cited_by_count":9,"area":null},{"id":"2404.10989","title":"FairSSD: Understanding Bias in Synthetic Speech Detectors","created":"2024-04-17","cited_by_count":9,"area":null},{"id":"2406.03512","title":"Harder or Different? Understanding Generalization of Audio Deepfake Detection","created":"2024-06-05","cited_by_count":9,"area":null},{"id":"2408.17352","title":"AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2505.11109","title":"MAVOS-DD: Multilingual Audio-Video Open-Set Deepfake Detection Benchmark","created":"2025-05-16","cited_by_count":9,"area":null},{"id":"2407.18517","title":"SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection","created":"2024-07-26","cited_by_count":8,"area":null},{"id":"2309.15224","title":"Collaborative Watermarking for Adversarial Speech Synthesis","created":"2023-09-26","cited_by_count":7,"area":null},{"id":"2410.09869","title":"Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset","created":"2024-10-13","cited_by_count":7,"area":null},{"id":"2504.06753","title":"Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perception","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2508.04143","title":"Multilingual Source Tracing of Speech Deepfakes: A First Benchmark","created":"2025-08-06","cited_by_count":7,"area":null},{"id":"2509.07132","title":"Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2304.03323","title":"DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detection","created":"2023-04-06","cited_by_count":6,"area":null},{"id":"2403.01355","title":"a-DCF: an architecture agnostic metric with application to spoofing-robust speaker verification","created":"2024-03-03","cited_by_count":6,"area":null},{"id":"2408.05366","title":"The DeepSpeak Dataset","created":"2024-08-09","cited_by_count":6,"area":null},{"id":"2408.09300","title":"Malacopula: adversarial automatic speaker verification attacks using a neural-based generalised Hammerstein model","created":"2024-08-17","cited_by_count":6,"area":null},{"id":"2410.07379","title":"Learn from Real: Reality Defender's Submission to ASVspoof5 Challenge","created":"2024-10-09","cited_by_count":6,"area":null},{"id":"2505.22581","title":"Tell me Habibi, is it Real or Fake?","created":"2025-05-28","cited_by_count":6,"area":null},{"id":"2601.17782","title":"Shortcut Learning in Binary Classifier Black Boxes: Applications to Voice Anti-Spoofing and Biometrics","created":"2026-01-25","cited_by_count":6,"area":null},{"id":"2305.17739","title":"Range-Based Equal Error Rate for Spoof Localization","created":"2023-05-28","cited_by_count":5,"area":null},{"id":"2406.03240","title":"Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm with Real Emphasis and Fake Dispersion Strategy","created":"2024-06-05","cited_by_count":5,"area":null},{"id":"2408.15775","title":"Easy, Interpretable, Effective: openSMILE for voice deepfake detection","created":"2024-08-28","cited_by_count":5,"area":null},{"id":"2502.04230","title":"XAttnMark: Learning Robust Audio Watermarking with Cross-Attention","created":"2025-02-06","cited_by_count":5,"area":null},{"id":"2602.20805","title":"Assessing the Impact of Speaker Identity in Speech Spoofing Detection","created":"2026-02-24","cited_by_count":5,"area":null},{"id":"2409.13049","title":"DiffSSD: A Diffusion-Based Dataset For Speech Forensics","created":"2024-09-19","cited_by_count":4,"area":null},{"id":"2409.13382","title":"Audio Codec Augmentation for Robust Collaborative Watermarking of Speech Synthesis","created":"2024-09-20","cited_by_count":4,"area":null},{"id":"2411.17911","title":"Passive Deepfake Detection Across Multi-modalities: A Comprehensive Survey","created":"2024-11-26","cited_by_count":4,"area":null},{"id":"2505.23962","title":"Can Emotion Fool Anti-spoofing?","created":"2025-05-29","cited_by_count":4,"area":null},{"id":"2603.06164","title":"Do Compact SSL Backbones Matter for Audio Deepfake Detection? A Controlled Study with RAPTOR","created":"2026-03-06","cited_by_count":4,"area":null},{"id":"2309.12237","title":"t-EER: Parameter-Free Tandem Evaluation of Countermeasures and Biometric Comparators","created":"2023-09-21","cited_by_count":3,"area":null},{"id":"2404.19363","title":"Expressivity and Speech Synthesis","created":"2024-04-30","cited_by_count":3,"area":null},{"id":"2506.22783","title":"PhonemeFake: Redefining Deepfake Realism with Language-Driven Segmental Manipulation and Adaptive Bilevel Detection","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2509.09204","title":"Bona fide Cross Testing Reveals Weak Spot in Audio Deepfake Detection Systems","created":"2025-09-11","cited_by_count":3,"area":null},{"id":"2603.14767","title":"Investigating the Impact of Speech Enhancement on Audio Deepfake Detection in Noisy Environments","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.26856","title":"AFSS: Artifact-Focused Self-Synthesis for Mitigating Bias in Audio Deepfake Detection","created":"2026-03-27","cited_by_count":3,"area":null},{"id":"2604.08184","title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","created":"2026-04-09","cited_by_count":3,"area":null},{"id":"2405.05244","title":"SVDD Challenge 2024: A Singing Voice Deepfake Detection Challenge Evaluation Plan","created":"2024-05-08","cited_by_count":2,"area":null},{"id":"2406.17246","title":"Beyond Silence: Bias Analysis through Loss and Asymmetric Approach in Audio Anti-Spoofing","created":"2024-06-25","cited_by_count":2,"area":null},{"id":"2408.10853","title":"Does Current Deepfake Audio Detection Model Effectively Detect ALM-based Deepfake Audio?","created":"2024-08-20","cited_by_count":2,"area":null},{"id":"2503.17577","title":"Measuring the Robustness of Audio Deepfake Detection under Real-World Corruption","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2506.14153","title":"Pushing the Performance of Synthetic Speech Detection with Kolmogorov-Arnold Networks and Self-Supervised Learning Models","created":"2025-06-17","cited_by_count":2,"area":null},{"id":"2509.20682","title":"Addressing Gradient Misalignment in Data-Augmented Training for Robust Speech Deepfake Detection","created":"2025-09-25","cited_by_count":2,"area":null},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2306.15389","title":"Multi-perspective Information Fusion Res2Net with RandomSpecmix for Fake Speech Detection","created":"2023-06-27","cited_by_count":1,"area":null},{"id":"2402.14205","title":"Compression Robust Synthetic Speech Detection Using Patched Spectrogram Transformer","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2403.14290","title":"Exploring Green AI for Audio Deepfake Detection","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2504.15663","title":"FADEL: Uncertainty-aware Fake Audio Detection with Evidential Deep Learning","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2507.16206","title":"METER: Multi-modal Evidence-based Thinking and Explainable Reasoning -- Algorithm and Benchmark","created":"2025-07-22","cited_by_count":1,"area":null},{"id":"2508.10559","title":"Fake Speech Wild: Detecting Deepfake Speech on Social Media Platform","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.08283","title":"Segment Transformer: AI-Generated Music Detection via Music Structural Analysis","created":"2025-09-10","cited_by_count":1,"area":null},{"id":"2509.20679","title":"QAMO: Quality-aware Multi-centroid One-class Learning For Speech Deepfake Detection","created":"2025-09-25","cited_by_count":1,"area":null},{"id":"2509.26471","title":"On Deepfake Voice Detection -- It's All in the Presentation","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.06706","title":"XLSR-Kanformer: A KAN-Intergrated model for Synthetic Speech Detection","created":"2025-10-08","cited_by_count":1,"area":null},{"id":"2511.21325","title":"SONAR: Spectral-Contrastive Audio Residuals for Generalizable Deepfake Detection","created":"2025-11-26","cited_by_count":1,"area":null},{"id":"2512.23374","title":"NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2603.18657","title":"Enhancing Multi-Corpus Training in SSL-Based Anti-Spoofing Models: Domain-Invariant Feature Extraction","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.21875","title":"Disentangling Speaker Traits for Deepfake Source Verification via Chebyshev Polynomial and Riemannian Metric Learning","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2606.10911","title":"Ethical and Technical Limits of Deepfake Speech Datasets","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2607.03134","title":"Open-Set Source Tracing as Compositional Factors via Structured Prototypes","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2607.03150","title":"An Intervention-Based Framework for Shortcut Diagnosis in Spoofing Countermeasures","created":"2026-07-03","cited_by_count":1,"area":null},{"id":"2609.16458","title":"Language Orthogonalization for Zero-Shot Cross-Lingual Audio Deepfake Detection","created":"2026-09-15","cited_by_count":1,"area":null},{"id":"2309.08099","title":"Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection","created":"2023-09-15","cited_by_count":0,"area":null},{"id":"2402.17104","title":"Adversarial Perturbations of Physical Signals","created":"2024-02-27","cited_by_count":0,"area":null},{"id":"2403.05380","title":"Spectrogram-Based Detection of Auto-Tuned Vocals in Music Recordings","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2407.03514","title":"Towards Attention-based Contrastive Learning for Audio Spoof Detection","created":"2024-07-03","cited_by_count":0,"area":null},{"id":"2410.01108","title":"Augmentation through Laundering Attacks for Audio Spoof Detection","created":"2024-10-01","cited_by_count":0,"area":null},{"id":"2502.16584","title":"Audio-FLAN: An Instruction-Following Dataset for Unified Audio Understanding and Generation of Speech, Music, and Sound","created":"2025-02-23","cited_by_count":0,"area":null},{"id":"2506.07294","title":"Towards Generalized Source Tracing for Codec-Based Deepfake Speech","created":"2025-06-08","cited_by_count":0,"area":null},{"id":"2508.02521","title":"Towards Reliable Audio Deepfake Attribution and Model Recognition: A Multi-Level Autoencoder-Based Framework","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.20983","title":"Multilingual Dataset Integration Strategies for Robust Audio Deepfake Detection: A SAFE Challenge System","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.00186","title":"Generalizable Audio Spoofing Detection using Non-Semantic Representations","created":"2025-08-29","cited_by_count":0,"area":null},{"id":"2509.04150","title":"Revisiting Simple Baselines for In-The-Wild Deepfake Detection","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2509.14959","title":"Discrete optimal transport is a strong audio adversarial attack","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.21676","title":"HuLA: Prosody-Aware Anti-Spoofing with Multi-Task Learning for Expressive and Emotional Synthetic Speech","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.22808","title":"ArFake: A Robust Framework for Multi-Dialect Arabic Speech Spoofing Detection Benchmark","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2512.06040","title":"Audio Physical Dynamics Inspired Deepfake Detection for Voice Authentication Systems","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2601.20883","title":"VoxMorph: Scalable Zero-shot Voice Identity Morphing via Disentangled Embeddings","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.16399","title":"Multi-Channel Replay Speech Detection using Acoustic Maps","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.01482","title":"A SUPERB-Style Benchmark of Self-Supervised Speech Models for Audio Deepfake Detection","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.14033","title":"What Counts as Real? Speech Restoration and Voice Quality Conversion Pose New Challenges to Deepfake Detection","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.16749","title":"ICLAD: In-Context Learning with Comparison-Guidance for Audio Deepfake Detection","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2604.23241","title":"Spectro-Temporal Modulation Representation Framework for Human-Imitated Speech Detection","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2605.02223","title":"Toward Fine-Grained Speech Inpainting Forensics:A Dataset, Method, and Metric for Multi-Region Tampering Localization","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.28064","title":"I Hear, Therefore I Trust: A Socio-Technical Investigation of Humans as Synthetic Speech Detectors","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.08669","title":"A Comparison of SSL-Based Feature Extractors and Back-End Classifiers for Spoofing Detection: A Multi-Corpus Training and Cross-Linguistic Analysis","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2606.25328","title":"Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection","created":"2026-06-24","cited_by_count":0,"area":null}],"next_cursor":"100"}