تقرير
Texture Re-scalable Universal Adversarial Perturbation
العنوان: | Texture Re-scalable Universal Adversarial Perturbation |
---|---|
المؤلفون: | Huang, Yihao, Guo, Qing, Juefei-Xu, Felix, Hu, Ming, Jia, Xiaojun, Cao, Xiaochun, Pu, Geguang, Liu, Yang |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | Universal adversarial perturbation (UAP), also known as image-agnostic perturbation, is a fixed perturbation map that can fool the classifier with high probabilities on arbitrary images, making it more practical for attacking deep models in the real world. Previous UAP methods generate a scale-fixed and texture-fixed perturbation map for all images, which ignores the multi-scale objects in images and usually results in a low fooling ratio. Since the widely used convolution neural networks tend to classify objects according to semantic information stored in local textures, it seems a reasonable and intuitive way to improve the UAP from the perspective of utilizing local contents effectively. In this work, we find that the fooling ratios significantly increase when we add a constraint to encourage a small-scale UAP map and repeat it vertically and horizontally to fill the whole image domain. To this end, we propose texture scale-constrained UAP (TSC-UAP), a simple yet effective UAP enhancement method that automatically generates UAPs with category-specific local textures that can fool deep models more easily. Through a low-cost operation that restricts the texture scale, TSC-UAP achieves a considerable improvement in the fooling ratio and attack transferability for both data-dependent and data-free UAP methods. Experiments conducted on two state-of-the-art UAP methods, eight popular CNN models and four classical datasets show the remarkable performance of TSC-UAP. Comment: 14 pages (accepted by TIFS2024) |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2406.06089 |
رقم الأكسشن: | edsarx.2406.06089 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |