# Transferable Adversarial Attacks on Audio Deepfake Detection

arXiv: https://arxiv.org/abs/2501.11902 · HTML: https://mlsanity.com/paper/2501.11902/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2025.

## Built on by (most cited first, 9 of 9)

- [Adversarial Attacks on Audio Deepfake Detection: A Benchmark and Comparative Study](https://mlsanity.com/paper/2509.07132/) (2025)
- [TRACE: Training-Free Partial Audio Deepfake Detection via Embedding Trajectory Analysis of Speech Foundation Models](https://mlsanity.com/paper/2604.01083/) (2026)
- [Face2Parts: Exploring Coarse-to-Fine Inter-Regional Facial Dependencies for Generalized Deepfake Detection](https://mlsanity.com/paper/2603.26036/) (2026)
- [SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks](https://mlsanity.com/paper/2507.13170/) (2025)
- [Dual-Branch Gated Fusion for Open-Set Audio Deepfake Source Tracing](https://mlsanity.com/paper/2606.10223/) (2026)
- [Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models](https://mlsanity.com/paper/2506.11521/) (2025)
- [Uncertainty-Aware Deepfake Detection via Multi-View Structural Learning](https://mlsanity.com/paper/2607.28769/) (2026)
- [Unmasking Synthetic Realities in Generative AI: A Comprehensive Review of Adversarially Robust Deepfake Detection Systems](https://mlsanity.com/paper/2507.21157/) (2025)
- [PE-Mamba: Bidirectional Selective Layer Aggregation for AI-Generated Image Detection](https://mlsanity.com/paper/2608.07999/) (2026)

## Abstract (arXiv)

Audio deepfakes pose significant threats, including impersonation, fraud, and reputation damage. To address these risks, audio deepfake detection (ADD) techniques have been developed, demonstrating success on benchmarks like ASVspoof2019. However, their resilience against transferable adversarial attacks remains largely unexplored. In this paper, we introduce a transferable GAN-based adversarial attack framework to evaluate the effectiveness of state-of-the-art (SOTA) ADD systems. By leveraging an ensemble of surrogate ADD models and a discriminator, the proposed approach generates transferable adversarial attacks that better reflect real-world scenarios. Unlike previous methods, the proposed framework incorporates a self-supervised audio model to ensure transcription and perceptual integrity, resulting in high-quality adversarial attacks. Experimental results on benchmark dataset reveal that SOTA ADD systems exhibit significant vulnerabilities, with accuracies dropping from 98% to 26%, 92% to 54%, and 94% to 84% in white-box, gray-box, and black-box scenarios, respectively. When tested in other data sets, performance drops of 91% to 46%, and 94% to 67% were observed against the In-the-Wild and WaveFake data sets, respectively. These results highlight the significant vulnerabilities of existing ADD systems and emphasize the need to enhance their robustness against advanced adversarial threats to ensure security and reliability.