Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
Preprint
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 its robustness has become critically significant. JPEG AI is among the first international, real-world applications of neural-network-based models to be embedded in consumer devices. However, research on NIC robustness has been limited to open-source codecs and a narrow range of attacks. This paper proposes a new methodology for measuring NIC robustness to adversarial attacks. We present the first large-scale evaluation of JPEG AI's robustness, comparing it with other NIC models. Our evaluation results and code are publicly available online (link is hidden for a blind review).Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Physical Adversarial Attack Meets Computer Vision: A Decade SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- The JPEG AI Standard: Providing Efficient Human and Machine Visual Data ConsumptionIEEE MultiMedia, 2023
- A survey on adversarial attacks and defencesCAAI Transactions on Intelligence Technology, 2021
- Boosting Adversarial Attacks with Momentum2018
- Contour Detection and Hierarchical Image SegmentationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2010
- Maximum differentiation (MAD) competition: A methodology for comparing computational models of perceptual quantitiesJournal of Vision, 2008
- The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observationsColor Research & Application, 2004