A universal deepfake detector has achieved the best accuracy yet in spotting multiple types of videos manipulated or completely generated by artificial intelligence. The technology may help flag non-consensual AI-generated pornography, deepfake scams or election misinformation videos. The widespread availability of cheap AI-powered deepfake creation tools has fuelled the out-of-control online spread of synthetic videos. Many depict women – including celebrities and even schoolgirls – in nonconsensual pornography. And deepfakes have also been used to influence political elections, as well as to enhance financial scams targeting both ordinary consumers and company executives. But most AI models trained to detect synthetic video focus on faces – which means they are most effective at spotting one specific type of deepfake, where a real person's face is swapped into an existing video.

Visual counterfeits are increasingly causing an existential conundrum in mainstream media with rapid evolution in neural image synthesis methods. Though detection of such counterfeits has been a taxing problem in the image forensics community, a recent class of forensic detectors -- universal detectors -- are able to surprisingly spot counterfeit images regardless of generator architectures, loss functions, training datasets, and resolutions. This intriguing property suggests the possible existence of transferable forensic features (T-FF) in universal detectors. In this work, we conduct the first analytical study to discover and understand T-FF in universal detectors. Our contributions are 2-fold: 1) We propose a novel forensic feature relevance statistic (FF-RS) to quantify and discover T-FF in universal detectors and, 2) Our qualitative and quantitative investigations uncover an unexpected finding: color is a critical T-FF in universal detectors. Code and models are available at https://keshik6.github.io/transferable-forensic-features/