The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples
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 testing samples in order to make classifier misclassify the given data. Adversarial attacks use these intentionally generated examples and they pose a security risk to the machine learning based systems. To be immune to such attacks, it is desirable to have a pre-processing mechanism which removes these effects causing misclassification while keeping the content of the image. JPEG and JPEG2000 are well-known image compression techniques which suppress the high-frequency content taking the human visual system into account. JPEG has been also shown to be an effective method for reducing adversarial noise. In this paper, we propose applying JPEG2000 compression as an alternative and systematically compare the classification performance of adversarial images compressed using JPEG and JPEG2000 at different target PSNR values and maximum compression levels. Our experiments show that JPEG2000 is more effective in reducing adversarial noise as it allows higher compression rates with less distortion and it does not introduce blocking artifacts.
Code (0)
등록된 구현이 없습니다.
Tasks
BlockingImage CompressionSimilar Papers 제목 키워드 기반
Improving the JPEG-resistance of Adversarial Attacks on Face Recognition by Interpolation Smoothing
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 RecognitionKeeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression
Deep neural networks (DNNs) have achieved great success in solving a variety of machine learning (ML) problems, especially in the domain of image recognition. However, recent research showed that DNNs can be highly vulne…
JPEG Inspired Deep Learning
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+2JPEG-resistant Adversarial Images
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…
Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods
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 stan…
Adversarial RobustnessImage Compression