Partially-Connected Differentiable Architecture Search for Deepfake and Spoofing Detection
This addresses the problem of efficient and effective detection of manipulated media for security applications, though it is incremental as it adapts an existing method to a new domain.
The paper tackled deepfake and spoofing detection by applying a differentiable architecture search (DARTS) approach, resulting in networks that are competitive with state-of-the-art systems and contain up to 85% fewer parameters than a Res2Net competitor.
This paper reports the first successful application of a differentiable architecture search (DARTS) approach to the deepfake and spoofing detection problems. An example of neural architecture search, DARTS operates upon a continuous, differentiable search space which enables both the architecture and parameters to be optimised via gradient descent. Solutions based on partially-connected DARTS use random channel masking in the search space to reduce GPU time and automatically learn and optimise complex neural architectures composed of convolutional operations and residual blocks. Despite being learned quickly with little human effort, the resulting networks are competitive with the best performing systems reported in the literature. Some are also far less complex, containing 85% fewer parameters than a Res2Net competitor.