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

• URL: http://arxiv.org/abs/2506.19051v1
• Date: Mon, 23 Jun 2025 19:11:15 GMT
• Title: NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
• Authors: Georgii Bychkov, Khaled Abud, Egor Kovalev, Alexander Gushchin, Dmitriy Vatolin, Anastasia Antsiferova,
• Abstract summary: JPEG AI is the first standard for end-to-end neural image compression (NIC) methods.<n>Previous research has been limited to a narrow range of codecs and attacks.<n>We present textbfNIC-RobustBench, the first open-source framework to evaluate NIC robustness and adversarial defenses' efficiency.
• Score: 39.50289486200944
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Adversarial robustness of neural networks is an increasingly important area of research, combining studies on computer vision models, large language models (LLMs), and others. With the release of JPEG AI -- the first standard for end-to-end neural image compression (NIC) methods -- the question of evaluating NIC robustness has become critically significant. However, previous research has been limited to a narrow range of codecs and attacks. To address this, we present \textbf{NIC-RobustBench}, the first open-source framework to evaluate NIC robustness and adversarial defenses' efficiency, in addition to comparing Rate-Distortion (RD) performance. The framework includes the largest number of codecs among all known NIC libraries and is easily scalable. The paper demonstrates a comprehensive overview of the NIC-RobustBench framework and employs it to analyze NIC robustness. Our code is available online at https://github.com/msu-video-group/NIC-RobustBench.

Related papers

• Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods [37.328379777238304]
  JPEG AI is the first standard for end-to-end neural image compression methods. This paper presents the first large-scale evaluation of JPEG AI's robustness.
  arXiv  Detail & Related papers  (2024-11-18T18:08:52Z)
• Neural Image Compression: Generalization, Robustness, and Spectral Biases [16.55855347335981]
  Recent advances in neural image compression (NIC) have produced models that are starting to outperform classic codecs. Successful adoption of any machine learning system in the wild requires it to generalize (and be robust) to unseen distribution shifts. This paper presents a benchmark suite to evaluate the out-of-distribution performance of image compression methods.
  arXiv  Detail & Related papers  (2023-07-17T17:14:17Z)
• Continuous U-Net: Faster, Greater and Noiseless [2.6163085620813287]
  We introduce continuous U-Net, a novel family of networks for image segmentation. We provide theoretical guarantees for our network demonstrating faster convergence, higher robustness and less sensitivity to noise. We demonstrate, through extensive numerical and visual results, that our model outperforms existing U-Net blocks for several medical image segmentation benchmarking datasets.
  arXiv  Detail & Related papers  (2023-02-01T17:46:00Z)
• Multi-Sample Training for Neural Image Compression [11.167668701825134]
  Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient of evidence lower bound (ELBO) We propose to train NIC with multiple-sample importance weighted autoencoder (IWAE) target, which is tighter than ELBO and converges to log likelihood as sample size increases. Our MS-NIC is plug-and-play, and can be easily extended to other neural compression tasks.
  arXiv  Detail & Related papers  (2022-09-28T04:42:02Z)
• KXNet: A Model-Driven Deep Neural Network for Blind Super-Resolution [57.882146858582175]
  We propose a model-driven deep neural network, called KXNet, for blind SISR. The proposed KXNet is fully integrated with the inherent physical mechanism underlying this SISR task. Experiments on synthetic and real data finely demonstrate the superior accuracy and generality of our method.
  arXiv  Detail & Related papers  (2022-09-21T12:22:50Z)
• InDuDoNet+: A Model-Driven Interpretable Dual Domain Network for Metal Artifact Reduction in CT Images [53.4351366246531]
  We construct a novel interpretable dual domain network, termed InDuDoNet+, into which CT imaging process is finely embedded. We analyze the CT values among different tissues, and merge the prior observations into a prior network for our InDuDoNet+, which significantly improve its generalization performance.
  arXiv  Detail & Related papers  (2021-12-23T15:52:37Z)
• Neural network relief: a pruning algorithm based on neural activity [47.57448823030151]
  We propose a simple importance-score metric that deactivates unimportant connections. We achieve comparable performance for LeNet architectures on MNIST. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations.
  arXiv  Detail & Related papers  (2021-09-22T15:33:49Z)
• Rate Distortion Characteristic Modeling for Neural Image Compression [59.25700168404325]
  End-to-end optimization capability offers neural image compression (NIC) superior lossy compression performance. distinct models are required to be trained to reach different points in the rate-distortion (R-D) space. We make efforts to formulate the essential mathematical functions to describe the R-D behavior of NIC using deep network and statistical modeling.
  arXiv  Detail & Related papers  (2021-06-24T12:23:05Z)
• On the Adversarial Robustness of Quantized Neural Networks [2.0625936401496237]
  It is unclear how model compression techniques may affect the robustness of AI algorithms against adversarial attacks. This paper explores the effect of quantization, one of the most common compression techniques, on the adversarial robustness of neural networks.
  arXiv  Detail & Related papers  (2021-05-01T11:46:35Z)
• Searching Central Difference Convolutional Networks for Face Anti-Spoofing [68.77468465774267]
  Face anti-spoofing (FAS) plays a vital role in face recognition systems. Most state-of-the-art FAS methods rely on stacked convolutions and expert-designed network. Here we propose a novel frame level FAS method based on Central Difference Convolution (CDC)
  arXiv  Detail & Related papers  (2020-03-09T12:48:37Z)
• Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond [171.07853346630057]
  Linear relaxation based perturbation analysis (LiRPA) for neural networks has become a core component in robustness verification and certified defense. We develop an automatic framework to enable perturbation analysis on any neural network structures. We demonstrate LiRPA based certified defense on Tiny ImageNet and Downscaled ImageNet.
  arXiv  Detail & Related papers  (2020-02-28T18:47:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.