Adversarial mimicry attacks against image splicing forensics: An approach for jointly hiding manipulations and creating false detections

Giulia Boato, Francesco G. B. De Natale, Gianluca De Stefano, Cecilia Pasquini, Fabio Roli

Abstract: Highlights•The proposed mimicry attack hides forgeries in images and introduces fictitious ones•It allows adversaries to introduce semantic biases and mislead the forensic detection•Its large-scale adoption may hinder the trust on forensic tools, akin to DoS attacks•Sequential detector-specific attacks enable tackling multiple detectors at once

External IDs:dblp:journals/prl/BoatoNSPR24