A survey of machine learning techniques in adversarial image forensics. Issue 100 (January 2021)

• Record Type: Journal Article
• Authors: Nowroozi, Ehsan; Dehghantanha, Ali; Parizi, Reza M.; Choo, Kim-Kwang Raymond
• Is Part Of: Computers & security. Issue 100(2021)
• Publication Date: 2021-01
• Subjects: Image forensics -- Adversarial machine learning -- Adversarial learning -- Adversarial setting -- Image manipulation detection -- Cyber security; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2020.102092
• Languages: English
• ISSNs: 0167-4048

Abstract

Highlights: Machine learning techniques in adversarial image forensics. SVM and CCN-based image forensics and adversarial image forensics. Intrinsically robust machine learning engines against adversarial attacks. The need for repeatable and transferable attack payloads. Generative adversarial networks (GANs) in (adversarial) image forensics. Graphical abstract: Abstract: Image forensic plays a crucial role in both criminal investigations (e.g., dissemination of fake images to spread racial hate or false narratives about specific ethnicity groups or political campaigns) and civil litigation (e.g., defamation). Increasingly, machine learning approaches are also utilized in image forensics. However, there are also a number of limitations and vulnerabilities associated with machine learning-based approaches (e.g., how to detect adversarial (image) examples), and there are associated real-world consequences (e.g., inadmissible evidence, or wrongful conviction). Therefore, with a focus on image forensics, this paper surveys techniques that can be used to enhance the robustness of machine learning-based binary manipulation detectors in various adversarial scenarios.