A Survey of Machine Learning Techniques in Adversarial Image Forensics

TL;DR

This paper surveys machine learning techniques in image forensics, emphasizing their applications, limitations, and vulnerabilities, especially in detecting manipulated images under adversarial conditions, to improve forensic robustness.

Contribution

It provides a comprehensive review of ML methods in image forensics, highlighting challenges and potential solutions for adversarial robustness.

Findings

ML techniques are widely used in image forensics.

Adversarial examples pose significant challenges to ML-based detectors.

Enhancing robustness is crucial for reliable forensic analysis.

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) 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, for example how to detect adversarial (image) examples, with 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.