Effectiveness of random deep feature selection for securing image manipulation detectors against adversarial examples

by

Conference Paper1
Authors: Mauro Barni, Ehsan Nowroozi, Benedetta Tondi, Bowen Zhang
Year: 2020
Abstract: We investigate if the random feature selection approach proposed in [1] to improve the robustness of forensic detectors to targeted attacks, can be extended to detectors based on deep learning features. In particular, we study the transferability of adversarial examples targeting an original CNN image manipulation detector to other detectors (a fully connected neural network and a linear SVM) that rely on a random subset of the features extracted from the flatten layer of the original network…….