BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection
This addresses the risk of malicious abuse of synthesized images by improving robustness for unseen domains, though it is incremental as it builds on known frequency artifacts.
The paper tackles the problem of generalizing deepfake detection to unseen generative models and object categories by proposing Bilateral High-Pass Filters (BiHPF) to amplify frequency-level artifacts, resulting in outperforming state-of-the-art methods in cross-domain tests.
The advancement in numerous generative models has a two-fold effect: a simple and easy generation of realistic synthesized images, but also an increased risk of malicious abuse of those images. Thus, it is important to develop a generalized detector for synthesized images of any GAN model or object category, including those unseen during the training phase. However, the conventional methods heavily depend on the training settings, which cause a dramatic decline in performance when tested with unknown domains. To resolve the issue and obtain a generalized detection ability, we propose Bilateral High-Pass Filters (BiHPF), which amplify the effect of the frequency-level artifacts that are known to be found in the synthesized images of generative models. Numerous experimental results validate that our method outperforms other state-of-the-art methods, even when tested with unseen domains.