mlsanityData to 14 Oct 2026

Defense Against Adversarial Attacks on Audio DeepFake Detection

arXiv 2212.14597 ↗First posted 30 Dec 2022cs.SD cs.CR cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Audio DeepFakes (DF) are artificially generated utterances created using deep learning, with the primary aim of fooling the listeners in a highly convincing manner. Their quality is sufficient to pose a severe threat in terms of security and privacy, including the reliability of news or defamation. Multiple neural network-based methods to detect generated speech have been proposed to prevent the threats. In this work, we cover the topic of adversarial attacks, which decrease the performance of detectors by adding superficial (difficult to spot by a human) changes to input data. Our contribution contains evaluating the robustness of 3 detection architectures against adversarial attacks in two scenarios (white-box and using transferability) and enhancing it later by using adversarial training performed by our novel adaptive training. Moreover, one of the investigated architectures is RawNet3, which, to the best of our knowledge, we adapted for the first time to DeepFake detection.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 25 of its 34 references that are in the map. First posted on arXiv 30 Dec 2022.

Builds on

25 of 34 references.

References · 25

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  7. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
  8. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  9. 2021Are Transformers More Robust Than CNNs?cited by 187
  10. 2021FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Datasetcited by 181
  11. 2020End-to-end anti-spoofing with RawNet2cited by 164
  12. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
13 more
  1. 2022Does Audio Deepfake Detection Generalize?cited by 135
  2. 2015A Light CNN for Deep Face Representation with Noisy Labelscited by 126
  3. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 85
  4. 2021Deepfakes Generation and Detection: State-of-the-art, open challenges, countermeasures, and way forwardcited by 82
  5. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  6. 2022Pushing the limits of raw waveform speaker recognitioncited by 51
  7. 2021Investigating self-supervised front ends for speech spoofing countermeasurescited by 46
  8. 2022Practical Evaluation of Adversarial Robustness via Adaptive Auto Attackcited by 44
  9. 2019Adversarial Attacks on Spoofing Countermeasures of automatic speaker verificationcited by 23
  10. 2020Tandem Assessment of Spoofing Countermeasures and Automatic Speaker Verification: Fundamentalscited by 22
  11. 2020Defense against adversarial attacks on spoofing countermeasures of ASVcited by 20
  12. 2022Attack Agnostic Dataset: Towards Generalization and Stabilization of Audio DeepFake Detectioncited by 9
  13. 2022SpecRNet: Towards Faster and More Accessible Audio DeepFake Detectioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 6; 2026: 3.

12 papers.

  1. 2025Detect All-Type Deepfake Audio: Wavelet Prompt Tuning for Enhanced Auditory Perceptioncited by 7
  2. 2025Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Studycited by 7
  3. 2026Interpretable All-Type Audio Deepfake Detection with Audio LLMs via Frequency-Time Reinforcement Learningcited by 6
  4. 2024Passive Deepfake Detection Across Multi-modalities: A Comprehensive Surveycited by 4
  5. 2025SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attackscited by 3
  6. 2025Reliable Audio Deepfake Detection in Variable Conditions via Quantum-Kernel SVMscited by 3
  7. 2026AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plancited by 3
  8. 2024Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learningcited by 1
  9. 2024D-CAPTCHA++: A Study of Resilience of Deepfake CAPTCHA under Transferable Imperceptible Adversarial Attackcited by 1
  10. 2025Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systemscited by 0
  11. 2025Zero-Shot to Zero-Lies: Detecting Bengali Deepfake Audio through Transfer Learningcited by 0
  12. 2026Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Studycited by 0