Paired-Sampling Contrastive Framework for Joint Physical-Digital Face Attack Detection
This addresses the vulnerability of face recognition systems to combined attack vectors by reducing system complexity and latency, though it is incremental as it builds on existing contrastive learning approaches.
The paper tackles the problem of detecting both physical and digital face spoofing attacks with a unified model, achieving an average classification error rate of 2.10% on a benchmark, which outperforms prior solutions.
Modern face recognition systems remain vulnerable to spoofing attempts, including both physical presentation attacks and digital forgeries. Traditionally, these two attack vectors have been handled by separate models, each targeting its own artifacts and modalities. However, maintaining distinct detectors increases system complexity and inference latency and leaves systems exposed to combined attack vectors. We propose the Paired-Sampling Contrastive Framework, a unified training approach that leverages automatically matched pairs of genuine and attack selfies to learn modality-agnostic liveness cues. Evaluated on the 6th Face Anti-Spoofing Challenge Unified Physical-Digital Attack Detection benchmark, our method achieves an average classification error rate (ACER) of 2.10 percent, outperforming prior solutions. The framework is lightweight (4.46 GFLOPs) and trains in under one hour, making it practical for real-world deployment. Code and pretrained models are available at https://github.com/xPONYx/iccv2025_deepfake_challenge.