English

On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors

Computer Vision and Pattern Recognition 2026-04-09 v2 Artificial Intelligence

Abstract

Modern image compression methods are typically optimized for the rate--distortion--perception trade-off, whereas their robustness to bit-level corruption is rarely examined. We show that diffusion-based compressors built on the Reverse Channel Coding (RCC) paradigm are substantially more robust to bit flips than classical and learned codecs. We further introduce a more robust variant of Turbo-DDCM that significantly improves robustness while only minimally affecting the rate--distortion--perception trade-off. Our findings suggest that RCC-based compression can yield more resilient compressed representations, potentially reducing reliance on error-correcting codes in highly noisy environments.

Keywords

Cite

@article{arxiv.2604.05743,
  title  = {On the Robustness of Diffusion-Based Image Compression to Bit-Flip Errors},
  author = {Amit Vaisman and Gal Pomerants and Raz Lapid},
  journal= {arXiv preprint arXiv:2604.05743},
  year   = {2026}
}

Comments

Accepted at AIGENS @ CVPR 2026

R2 v1 2026-07-01T11:57:12.738Z