Toward Reliable Models for Authenticating Multimedia Content: Detecting Resampling Artifacts With Bayesian Neural Networks

TL;DR

This paper introduces Bayesian neural networks for multimedia forensic tasks, enhancing detection accuracy and out-of-distribution sample identification, thereby improving reliability in authenticity verification of images and videos.

Contribution

It pioneers the application of Bayesian neural networks in multimedia forensics, providing uncertainty estimates and robustness against unseen data variations.

Findings

State-of-the-art resampling detection performance

Effective detection of out-of-distribution samples

Robustness to unseen resampling factors and compression

Abstract

In multimedia forensics, learning-based methods provide state-of-the-art performance in determining origin and authenticity of images and videos. However, most existing methods are challenged by out-of-distribution data, i.e., with characteristics that are not covered in the training set. This makes it difficult to know when to trust a model, particularly for practitioners with limited technical background. In this work, we make a first step toward redesigning forensic algorithms with a strong focus on reliability. To this end, we propose to use Bayesian neural networks (BNN), which combine the power of deep neural networks with the rigorous probabilistic formulation of a Bayesian framework. Instead of providing a point estimate like standard neural networks, BNNs provide distributions that express both the estimate and also an uncertainty range. We demonstrate the usefulness of this framework on a classical forensic task: resampling detection. The BNN yields state-of-the-art detection performance, plus excellent capabilities for detecting out-of-distribution samples. This is demonstrated for three pathologic issues in resampling detection, namely unseen resampling factors, unseen JPEG compression, and unseen resampling algorithms. We hope that this proposal spurs further research toward reliability in multimedia forensics.