Adversarial Perturbations Fool Deepfake Detectors
Adversarial Perturbations Fool Deepfake Detectors
This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. We created adversarial perturbations using the Fast Gradient Sign Method and the Carlini and Wagner L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> norm attack in both blackbox and whitebox settings. Detectors achieved over 95% accuracy on unperturbed deepfakes, but …