NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
Adversarial purification has achieved great success in combating adversarial image perturbations, which are usually assumed to be additive. However, non-additive adversarial perturbations such as blur, occlusion, and distortion are also common in the real world. Under such perturbations, existing adversarial purification methods are much less effective since they are designed to fit the additive nature. In this paper, we propose an extended adversarial purification framework named NAPPure, which can further handle non-additive perturbations. Specifically, we first establish the generation process of an adversarial image, and then disentangle the underlying clean image and perturbation parameters through likelihood maximization. Experiments on GTSRB and CIFAR-10 datasets show that NAPPure significantly boosts the robustness of image classification models against non-additive perturbations.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationSimilar Papers 제목 키워드 기반
Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information
Adversarial purification is one of the promising approaches to defend neural networks against adversarial attacks. Recently, methods utilizing diffusion probabilistic models have achieved great success for adversarial pu…
Adversarial PurificationAdversarial RobustnessDenoisingimage-classification+1Instant Adversarial Purification with Adversarial Consistency Distillation
Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise. Although some diffusion-based purification me…
Adversarial Purificationimage-classificationImage ClassificationGuided Diffusion Model for Adversarial Purification
With wider application of deep neural networks (DNNs) in various algorithms and frameworks, security threats have become one of the concerns. Adversarial attacks disturb DNN-based image classifiers, in which attackers ca…
Adversarial PurificationDenoisingmodelCLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification
In this paper, we aim to build an adversarially robust zero-shot image classifier. We ground our work on CLIP, a vision-language pre-trained encoder model that can perform zero-shot classification by matching an image wi…
Denoisingzero-shot-classificationZero-Shot LearningAdversarial purification with Score-based generative models
While adversarial training is considered as a standard defense method against adversarial attacks for image classifiers, adversarial purification, which purifies attacked images into clean images with a standalone purifi…
Adversarial PurificationDenoising