paper-with-me

홈 › Papers

CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification

2021-02-15 · Mingu Kang, Trung Quang Tran, Seungju Cho, Daeyoung Kim

Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead to erroneous predictions, resulting in catastrophic accidents. To mitigate the effects of adversarial attacks, we propose a novel purification model called CAP-GAN. CAP-GAN takes account of the idea of pixel-level and feature-level consistency to achieve reasonable purification under cycle-consistent learning. Specifically, we utilize the guided attention module and knowledge distillation to convey meaningful information to the purification model. Once a model is fully trained, inputs would be projected into the purification model and transformed into clean-like images. We vary the capacity of the adversary to argue the robustness against various types of attack strategies. On the CIFAR-10 dataset, CAP-GAN outperforms other pre-processing based defenses under both black-box and white-box settings.

📄 PDF Abstract BibTeX arXiv:2102.07304

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial RobustnessKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Robust Evaluation of Diffusion-Based Adversarial Purification

2023-03-16 · ICCV 2023 1 · Minjong Lee, Dongwoo Kim

We question the current evaluation practice on diffusion-based purification methods. Diffusion-based purification methods aim to remove adversarial effects from an input data point at test time. The approach gains increa…

Adversarial Purification

Self-supervised Adversarial Purification for Graph Neural Networks

2026-05-22 · Woohyun Lee, Hogun Park arxiv

Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by traditional methods like adversarial training that intertwine these conflicti…

Universal Adversarial Purification with DDIM Metric Loss for Stable Diffusion

2026-01-12 · Li Zheng, Liangbin Xie, Jiantao Zhou, He YiMin arxiv

Stable Diffusion (SD) often produces degraded outputs when the training dataset contains adversarial noise. Adversarial purification offers a promising solution by removing adversarial noise from contaminated data. Howev…

LoRID: Low-Rank Iterative Diffusion for Adversarial Purification

2024-09-12 · Geigh Zollicoffer, Minh Vu, Ben Nebgen, Juan Castorena 외

This work presents an information-theoretic examination of diffusion-based purification methods, the state-of-the-art adversarial defenses that utilize diffusion models to remove malicious perturbations in adversarial ex…

Adversarial PurificationDenoising

Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology

2026-06-07 · Zhe Li, Bernhard Kainz arxiv

Deep learning has become prevalent in computational pathology pipelines that support tasks such as cancer screening and digital pathology analysis. However, the susceptibility of neural networks to adversarial perturbati…

Adversarial Robustness