Region-based Optimization In Continual Learning For Audio Deepfake Detection

Abstract

Rapid advancements in speech synthesis and voice conversion bring convenience but also new security risks, creating an urgent need for effective audio deepfake detection. Although current models perform well, their effectiveness diminishes when confronted with the diverse and evolving nature of real-world deepfakes. To address this issue, we propose a continual learning method named Region-Based Optimization (RegO) for audio deepfake detection. Specifically, we use the Fisher information matrix to measure important neuron regions for real and fake audio detection, dividing them into four regions. First, we directly fine-tune the less important regions to quickly adapt to new tasks. Next, we apply gradient optimization in parallel for regions important only to real audio detection, and in orthogonal directions for regions important only to fake audio detection. For regions that are important to both, we use sample proportion-based adaptive gradient optimization. This region-adaptive opt

Stats

• citations1
• S2 citations—
• github stars12
• HF likes0
• heat score4.49
• arxiv keychen2024region

Related papers

• What To Remember: Self-adaptive Continual Learning For Audio Deepfake Detection (2023)10.48
• Towards Robust Audio Deepfake Detection: A Evolving Benchmark For Continual Learning (2024)0.00
• Adaptive Re-calibration Of Channel-wise Features For Adversarial Audio Classification (2022)0.00
• Generalized Source Tracing: Detecting Novel Audio Deepfake Algorithm With Real Emphasis And Fake Dispersion Strategy (2024)5.84
• Continual Learning For Fake Audio Detection (2021)11.49
• Deep Residual Neural Networks For Audio Spoofing Detection (2019)0.00
• Multi-modal Deepfake Detection And Localization With Fpn-transformer (2025)2.23
• Transsionadd: A Multi-frame Reinforcement Based Sequence Tagging Model For Audio Deepfake Detection (2023)0.00