Solutions to Deepfakes: Can Camera Hardware, Cryptography, and Deep Learning Verify Real Images?

TL;DR

This paper reviews methods combining camera hardware, cryptography, and deep learning to verify the authenticity of images amid the rise of indistinguishable generative AI content.

Contribution

It systematically analyzes existing detection and cryptographic strategies for verifying real images and discusses potential improvements to address current limitations.

Findings

Cryptography can enhance image verification security

Deep learning methods show promise but face challenges in generalization

Combining hardware and software approaches improves detection accuracy

Abstract

The exponential progress in generative AI poses serious implications for the credibility of all real images and videos. There will exist a point in the future where 1) digital content produced by generative AI will be indistinguishable from those created by cameras, 2) high-quality generative algorithms will be accessible to anyone, and 3) the ratio of all synthetic to real images will be large. It is imperative to establish methods that can separate real data from synthetic data with high confidence. We define real images as those that were produced by the camera hardware, capturing a real-world scene. Any synthetic generation of an image or alteration of a real image through generative AI or computer graphics techniques is labeled as a synthetic image. To this end, this document aims to: present known strategies in detection and cryptography that can be employed to verify which images are real, weight the strengths and weaknesses of these strategies, and suggest additional improvements to alleviate shortcomings.