mlsanityData to 14 Oct 2026

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

arXiv 2604.05743 ↗First posted 7 Apr 2026cs.CV cs.AIcited by 0

On the map: Diffusion models → Diffusion for compression and wireless

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion for compression and wireless, one of 14 directions in Diffusion models. Builds on 22 of its 37 references that are in the map. First posted on arXiv 7 Apr 2026.

Builds on

22 of 37 references.

Closest ancestors · 8

Same direction, newest first

  1. 2025Turbo-DDCM: Fast and Flexible Zero-Shot Diffusion-Based Image Compression9 Nov
  2. 2025StableCodec: Taming One-Step Diffusion for Extreme Image Compression27 Jun
  3. 2025Compressed Image Generation with Denoising Diffusion Codebook Models3 Feb
  4. 2025Lossy Compression with Pretrained Diffusion Models16 Jan
  5. 2024PSC: Posterior Sampling-Based Compression13 Jul
  6. 2023High-Fidelity Image Compression with Score-based Generative Models26 May
  7. 2022Lossy Image Compression with Conditional Diffusion Models14 Sep
  8. 2022Lossy Compression with Gaussian Diffusion17 Jun

Other references · 14

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2018Demystifying MMD GANscited by 1,293
  4. 2018Variational image compression with a scale hyperpriorcited by 935
  5. 2016End-to-end Optimized Image Compressioncited by 696
  6. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  7. 2020High-Fidelity Generative Image Compressioncited by 338
  8. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 301
  9. 2019Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoffcited by 211
  10. 2019Bit-Flip Attack: Crushing Neural Network with Progressive Bit Searchcited by 108
  11. 2023Towards image compression with perfect realism at ultra-low bitratescited by 103
  12. 2023Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Modelscited by 94
2 more
  1. 2020Channel-Aware Adversarial Attacks Against Deep Learning-Based Wireless Signal Classifierscited by 28
  2. 2024Deep Learning-Based Image Compression for Wireless Communications: Impacts on Reliability,Throughput, and Latencycited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Enhancing the Rate-Distortion-Perception Flexibility of Learned Image Codecs with Conditional Diffusion Decoders
  2. 2026Training-Free Rate-Distortion-Perception Traversal With Diffusion
  3. 2025Single-step Diffusion for Image Compression at Ultra-Low Bitrates
  4. 2024Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression
  5. 2024Lossy Image Compression with Foundation Diffusion Models
  6. 2021End-to-End Image Compression with Probabilistic Decoding
  7. 2026Rethinking Generative Image Compression at Extremely Low Bitrates
  8. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusion