NIC-RobustBench: A Comprehensive Open-Source Toolkit for Neural Image Compression and Robustness Analysis
This provides a toolkit for researchers and practitioners to analyze NIC robustness and adversarial defenses, though it is incremental as it builds on existing NIC and robustness research.
The authors tackled the problem of evaluating neural image compression (NIC) robustness, which has become important with the JPEG AI standard, by creating NIC-RobustBench, the first open-source framework for this purpose, which includes the largest number of codecs among known NIC libraries and is easily scalable.
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.