English

A Training-Free Defense Framework for Robust Learned Image Compression

Image and Video Processing 2024-01-23 v1 Computer Vision and Pattern Recognition

Abstract

We study the robustness of learned image compression models against adversarial attacks and present a training-free defense technique based on simple image transform functions. Recent learned image compression models are vulnerable to adversarial attacks that result in poor compression rate, low reconstruction quality, or weird artifacts. To address the limitations, we propose a simple but effective two-way compression algorithm with random input transforms, which is conveniently applicable to existing image compression models. Unlike the na\"ive approaches, our approach preserves the original rate-distortion performance of the models on clean images. Moreover, the proposed algorithm requires no additional training or modification of existing models, making it more practical. We demonstrate the effectiveness of the proposed techniques through extensive experiments under multiple compression models, evaluation metrics, and attack scenarios.

Keywords

Cite

@article{arxiv.2401.11902,
  title  = {A Training-Free Defense Framework for Robust Learned Image Compression},
  author = {Myungseo Song and Jinyoung Choi and Bohyung Han},
  journal= {arXiv preprint arXiv:2401.11902},
  year   = {2024}
}

Comments

10 pages and 14 figures

R2 v1 2026-06-28T14:23:27.211Z