FaceForensics++: Learning to Detect Manipulated Facial Images

TLDR

Synthetic image generation has advanced to a point that threatens societal trust and can spread misinformation. The study investigates how realistic current facial manipulation techniques are and how hard they are to detect by machines or humans. The authors introduce an automated benchmark using DeepFakes, Face2Face, FaceSwap, and NeuralTextures across varied compression and size, and conduct a comprehensive analysis of data‑driven detectors on this dataset. The benchmark, containing over 1.8 million manipulated images and a hidden test set, shows that incorporating domain‑specific knowledge yields unprecedented detection accuracy, surpassing human performance even under strong compression.

Abstract

The rapid progress in synthetic image generation and manipulation has now come to a point where it raises significant concerns for the implications towards society. At best, this leads to a loss of trust in digital content, but could potentially cause further harm by spreading false information or fake news. This paper examines the realism of state-of-the-art image manipulations, and how difficult it is to detect them, either automatically or by humans. To standardize the evaluation of detection methods, we propose an automated benchmark for facial manipulation detection. In particular, the benchmark is based on DeepFakes, Face2Face, FaceSwap and NeuralTextures as prominent representatives for facial manipulations at random compression level and size. The benchmark is publicly available and contains a hidden test set as well as a database of over 1.8 million manipulated images. This dataset is over an order of magnitude larger than comparable, publicly available, forgery datasets. Based on this data, we performed a thorough analysis of data-driven forgery detectors. We show that the use of additional domainspecific knowledge improves forgery detection to unprecedented accuracy, even in the presence of strong compression, and clearly outperforms human observers.