CVCRLGSep 19, 2020

Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering

arXiv:2009.09213v635 citations
Originality Incremental advance
AI Analysis

This addresses the arms race in DeepFake generation and detection, offering a way to improve future detection capabilities by creating more evasive fakes, though it is incremental in enhancing existing evasion techniques.

The paper tackles the problem of making DeepFake images evade detection by proposing DeepNotch, a method that reduces artifact patterns without compromising image quality, resulting in an average 36.79% reduction in detection accuracy across three state-of-the-art methods.

The current high-fidelity generation and high-precision detection of DeepFake images are at an arms race. We believe that producing DeepFakes that are highly realistic and 'detection evasive' can serve the ultimate goal of improving future generation DeepFake detection capabilities. In this paper, we propose a simple yet powerful pipeline to reduce the artifact patterns of fake images without hurting image quality by performing implicit spatial-domain notch filtering. We first demonstrate that frequency-domain notch filtering, although famously shown to be effective in removing periodic noise in the spatial domain, is infeasible for our task at hand due to the manual designs required for the notch filters. We, therefore, resort to a learning-based approach to reproduce the notch filtering effects, but solely in the spatial domain. We adopt a combination of adding overwhelming spatial noise for breaking the periodic noise pattern and deep image filtering to reconstruct the noise-free fake images, and we name our method DeepNotch. Deep image filtering provides a specialized filter for each pixel in the noisy image, producing filtered images with high fidelity compared to their DeepFake counterparts. Moreover, we also use the semantic information of the image to generate an adversarial guidance map to add noise intelligently. Our large-scale evaluation on 3 representative state-of-the-art DeepFake detection methods (tested on 16 types of DeepFakes) has demonstrated that our technique significantly reduces the accuracy of these 3 fake image detection methods, 36.79% on average and up to 97.02% in the best case.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes