Towards Robust Audio Deepfake Detection: A Evolving Benchmark For Continual Learning

Abstract

The rise of advanced large language models such as GPT-4, GPT-4o, and the Claude family has made fake audio detection increasingly challenging. Traditional fine-tuning methods struggle to keep pace with the evolving landscape of synthetic speech, necessitating continual learning approaches that can adapt to new audio while retaining the ability to detect older types. Continual learning, which acts as an effective tool for detecting newly emerged deepfake audio while maintaining performance on older types, lacks a well-constructed and user-friendly evaluation framework. To address this gap, we introduce EVDA, a benchmark for evaluating continual learning methods in deepfake audio detection. EVDA includes classic datasets from the Anti-Spoofing Voice series, Chinese fake audio detection series, and newly generated deepfake audio from models like GPT-4 and GPT-4o. It supports various continual learning techniques, such as Elastic Weight Consolidation (EWC), Learning without Forgetting (Lw

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2024towards

Related papers

• What To Remember: Self-adaptive Continual Learning For Audio Deepfake Detection (2023)10.48
• AUDETER: A Large-scale Dataset For Deepfake Audio Detection In Open Worlds (2025)0.00
• Continual Learning For Fake Audio Detection (2021)11.49
• FADEL: Uncertainty-aware Fake Audio Detection With Evidential Deep Learning (2025)0.00
• Adversarial Attacks On Audio Deepfake Detection: A Benchmark And Comparative Study (2025)0.00
• Zero-day Audio Deepfake Detection Via Retrieval Augmentation And Profile Matching (2025)0.00
• Benchmarking Audio Deepfake Detection Robustness In Real-world Communication Scenarios (2025)5.24
• Region-based Optimization In Continual Learning For Audio Deepfake Detection (2024)4.49