paper-with-me

Papers

NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations

2025-10-15 · Junjie Nan, Jianing Li, Wei Chen, Mingkun Zhang, Xueqi Cheng arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.14025

Code (0)

등록된 구현이 없습니다.

Tasks

Image Classification

Similar Papers 제목 키워드 기반

Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Information

2024-08-12 · Mingkun Zhang, Jianing Li, Wei Chen, Jiafeng Guo 외

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+1

Instant Adversarial Purification with Adversarial Consistency Distillation

2024-08-30 · CVPR 2025 1 · Chun Tong Lei, Hon Ming Yam, Zhongliang Guo, Chun Pong Lau

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 Classification

Guided Diffusion Model for Adversarial Purification

2022-05-30 · Jinyi Wang, Zhaoyang Lyu, Dahua Lin, Bo Dai 외

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 PurificationDenoisingmodel

CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification

2025-02-25 · Mingkun Zhang, Keping Bi, Wei Chen, Jiafeng Guo 외

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 Learning

Adversarial purification with Score-based generative models

2021-06-11 · Jongmin Yoon, Sung Ju Hwang, Juho Lee

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