paper-with-me

홈 › Papers

Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods

2024-11-18 · Egor Kovalev, Georgii Bychkov, Khaled Abud, Aleksandr Gushchin, Anna Chistyakova, Sergey Lavrushkin, Dmitriy Vatolin, Anastasia Antsiferova

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).

📄 PDF Abstract BibTeX arXiv:2411.11795

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessImage Compression

Similar Papers 제목 키워드 기반

JPEG Inspired Deep Learning

2024-10-09 · Ahmed H. Salamah, Kaixiang Zheng, YiWen Liu, En-hui Yang

Although it is traditionally believed that lossy image compression, such as JPEG compression, has a negative impact on the performance of deep neural networks (DNNs), it is shown by recent works that well-crafted JPEG co…

Deep LearningFine-Grained Image Classificationimage-classificationImage Classification+2

MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression

2021-08-18 · Zhaoyang Jia, Han Fang, Weiming Zhang

Based on the powerful feature extraction ability of deep learning architecture, recently, deep-learning based watermarking algorithms have been widely studied. The basic framework of such algorithm is the auto-encoder li…

JPEG-resistant Adversarial Images

2017-12-08 · NIPS 2017 Workshop on Machine Learning and Computer Security 2017 12 · Richard Shin, Dawn Song

Several papers have explored the use of JPEG compression as a defense against adversarial images. In this work, we show that we can generate adversarial images which survive JPEG compression, by including a differentiabl…

The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples

2018-03-28 · Ayse Elvan Aydemir, Alptekin Temizel, Tugba Taskaya Temizel

Adversarial examples are known to have a negative effect on the performance of classifiers which have otherwise good performance on undisturbed images. These examples are generated by adding non-random noise to the testi…

BlockingImage Compression

Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing

2024-02-26 · Kefu Guo, Fengfan Zhou, Hefei Ling, Ping Li 외

JPEG compression can significantly impair the performance of adversarial face examples, which previous adversarial attacks on face recognition (FR) have not adequately addressed. Considering this challenge, we propose a …

Adversarial AttackFace Recognition