The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.
Defense Against Adversarial Attacks on Audio DeepFake Detection
Open accessAbstract
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“they require sophisticated training procedures and increased computational overhead”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [204]
In the citing paper
“While adaptive method [204] achieve superior robustness”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [204]
In the citing paper
“Adaptive adversarial training [204] demonstrates exceptional performance against WAs, reducing ASR from 85 . 49% to 5 . 25%.”
From Deepfake detection across image, video, and audio: a comprehensive survey with empirical evaluation of generalization and robustness (2026) · cites this paper as [204]
Citations
Cites
The publisher hasn’t deposited this paper’s reference list.
Cited by
Nguyen-Le, H.-H., Tran, V.-T., Nguyen, D.-T., & Le-Khac, N.-A. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11608-4 · Cited by 28
Transferable Adversarial Attacks on Audio Deepfake Detection
Farooq, M. U., Khan, A. A., Uddin, K., & Malik, K. M. (2025) · IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW) · doi:10.1109/wacvw65960.2025.00178 · Cited by 35
Firc, A., Malinka, K., & Hanáček, P. (2025) · Cybersecurity · doi:10.1186/s42400-024-00346-1 · Cited by 33
Deepfake Detection in Video and Audio Clips: A Comprehensive Survey and Analysis
Jbara, W. A., Hussein, N. A.-H. K., & Soud, J. H. (2024) · Mesopotamian Journal of CyberSecurity · doi:10.58496/mjcs/2024/025 · Cited by 21
Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative StudyPreprint
Uddin, K., Farooq, M. U., Khan, A. A., & Malik, K. M. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.07132 · Cited by 16
Metadata
- Authors
- Kawa, P., Plata, M., & Syga, P.
- Venue
- INTERSPEECH 2023
- Publisher
- ISCA
- Published
- 2023-08-20
- Pages
- 5276-5280
- ISSN
- 2308-457X (ISSN-L)
- OpenAlex
- W4385823506
- Cited by
- 19
- References
- 0
- Citations by year
- 2026: 5 · 2025: 8 · 2024: 5 · 2023: 1
- FWCI
- 3.37
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- Interspeech (USB) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Department of Artificial Intelligence, Korea University
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Keywords
- audio deepfake detection, adversarial attacks, adversarial robustness, audio forensics, deepfake detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Defense Against Adversarial Attacks on Audio DeepFake Detection. https://app.cochat.ai/papers/10.21437/interspeech.2023-409
- The paper
- Kawa, P., Plata, M., & Syga, P. (2023). Defense Against Adversarial Attacks on Audio DeepFake Detection. INTERSPEECH 2023. https://doi.org/10.21437/interspeech.2023-409
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.