SLIC: Secure Learned Image Codec through Compressed Domain Watermarking to Defend Image Manipulation
Part Of
Proceedings of the 6th ACM International Conference on Multimedia in Asia, MMAsia 2024
Start Page
1
End Page
7
ISBN
979-840071273-9
Date Issued
2024-12-03
Author(s)
Chen-Hsiu Huang
DOI
10.1145/3696409.3700161
Abstract
The digital image manipulation and advancements in Generative AI, such as Deepfake, has raised significant concerns regarding the authenticity of images shared on social media. Traditional image forensic techniques, while helpful, are often passive and insufficient against sophisticated tampering methods. This paper introduces the Secure Learned Image Codec (SLIC), a novel active approach to ensuring image authenticity through watermark embedding in the compressed domain. SLIC leverages neural network-based compression to embed watermarks as adversarial perturbations in the latent space, creating images that degrade in quality upon re-compression if tampered with. This degradation acts as a defense mechanism against unauthorized modifications. Our method involves fine-tuning a neural encoder/decoder to balance watermark invisibility with robustness, ensuring minimal quality loss for non-watermarked images. Experimental results demonstrate SLIC's effectiveness in generating visible artifacts in tampered images, thereby preventing their redistribution. This work represents a significant step toward developing secure image codecs that can be widely adopted to safeguard digital image integrity.
Event(s)
6th ACM International Conference on Multimedia in Asia, MMAsia 2024
Publisher
ACM
Type
conference paper