mlsanityData to 14 Oct 2026

NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis

arXiv 2506.19051 ↗First posted 23 Jun 2025eess.IV cs.CV cs.MMcited by 1

Not on the map. Why?

Abstract (arXiv)

Neural image compression (NIC) is increasingly used in computer vision pipelines, as learning-based models are able to surpass traditional algorithms in compression efficiency. However, learned codecs can be unstable and vulnerable to adversarial attacks: small perturbations may cause severe reconstruction artifacts or indirectly break downstream models. Despite these risks, most NIC benchmarks only emphasize rate-distortion (RD) performance, focusing on model efficiency in safe, non-adversarial scenarios, while NIC robustness studies cover only specific codecs and attacks. To fill this gap, we introduce NIC-RobustBench, an open-source benchmark and evaluation framework for adversarial robustness of NIC methods. The benchmark integrates 8 attacks, 9 defense strategies, standard RD metrics, a large and extensible set of codecs, and tools for assessing both the robustness of the compression model and impact on downstream tasks. Using NIC-RobustBench, we provide a broad empirical study of modern NICs and defenses in adversarial scenarios, highlighting failure modes, least and most resilient architectures, and other insights into NIC robustness. Our code is available online at https://github.com/msu-video-group/NIC-RobustBench.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

39 of 52 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2024Depth Anything V2cited by 1,422
  8. 2018Variational image compression with a scale hyperpriorcited by 935
  9. 2021Multi-Stage Progressive Image Restorationcited by 816
  10. 2016End-to-end Optimized Image Compressioncited by 696
  11. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  12. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
27 more
  1. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  2. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  4. 2022Diffusion Models for Adversarial Purificationcited by 476
  5. 2020High-Fidelity Generative Image Compressioncited by 338
  6. 2017Sparsity Invariant CNNscited by 326
  7. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 301
  8. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 276
  9. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 211
  10. 2022Lossy Image Compression with Conditional Diffusion Modelscited by 170
  11. 2017Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representationscited by 152
  12. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 147
  13. 2018Adversarial Attacks and Defences Competitioncited by 96
  14. 2020Improving Inference for Neural Image Compressioncited by 83
  15. 2022Frequency-driven Imperceptible Adversarial Attack on Semantic Similaritycited by 77
  16. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  17. 2021A Survey On Universal Adversarial Attackcited by 59
  18. 2023EVC: Towards Real-Time Neural Image Compression with Mask Decaycited by 49
  19. 2021Slimmable Compressive Autoencoders for Practical Neural Image Compressioncited by 39
  20. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 35
  21. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 34
  22. 2022Video compression dataset and benchmark of learning-based video-quality metricscited by 27
  23. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 25
  24. 2023Comparing the Robustness of Modern No-Reference Image- and Video-Quality Metrics to Adversarial Attackscited by 14
  25. 2020Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detectioncited by 8
  26. 2024A Training-Free Defense Framework for Robust Learned Image Compressioncited by 5
  27. 2024JPEG AI Image Compression Visual Artifacts: Detection Methods and Datasetcited by 4

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025T-MLA: A targeted multiscale log-exponential attack framework for neural image compressioncited by 1