paper-with-me

홈 › Papers

Revisiting Adversarial Risk

2018-06-07 · Arun Sai Suggala, Adarsh Prasad, Vaishnavh Nagarajan, Pradeep Ravikumar

Recent works on adversarial perturbations show that there is an inherent trade-off between standard test accuracy and adversarial accuracy. Specifically, they show that no classifier can simultaneously be robust to adversarial perturbations and achieve high standard test accuracy. However, this is contrary to the standard notion that on tasks such as image classification, humans are robust classifiers with low error rate. In this work, we show that the main reason behind this confusion is the inexact definition of adversarial perturbation that is used in the literature. To fix this issue, we propose a slight, yet important modification to the existing definition of adversarial perturbation. Based on the modified definition, we show that there is no trade-off between adversarial and standard accuracies; there exist classifiers that are robust and achieve high standard accuracy. We further study several properties of this new definition of adversarial risk and its relation to the existing definition.

📄 PDF Abstract BibTeX arXiv:1806.02924

Code (0)

등록된 구현이 없습니다.

Tasks

image-classificationImage Classification

Similar Papers 제목 키워드 기반

Revisiting Min-Max Optimization Problem in Adversarial Training

2024-08-20 · Sina Hajer Ahmadi, Hassan Bahrami

The rise of computer vision applications in the real world puts the security of the deep neural networks at risk. Recent works demonstrate that convolutional neural networks are susceptible to adversarial examples - wher…

Deep Learning

Robust Regularization with Adversarial Labelling of Perturbed Samples

2021-05-28 · Xiaohui Guo, Richong Zhang, Yaowei Zheng, Yongyi Mao

Recent researches have suggested that the predictive accuracy of neural network may contend with its adversarial robustness. This presents challenges in designing effective regularization schemes that also provide strong…

Adversarial RobustnessComputational Efficiency

Revisiting Adversarial Training under Hyperspectral Image

2025-10-01 · Weihua Zhang, Chengze Jiang, Minjing Dong, Jie Gui 외 arxiv

Recent studies have shown that deep learning-based hyperspectral image (HSI) classification models are highly vulnerable to adversarial attacks, posing significant security risks. Although most approaches attempt to enha…

Image ClassificationData Augmentation

Revisiting Role of Autoencoders in Adversarial Settings

2020-05-21 · Byeong Cheon Kim, Jung Uk Kim, Hakmin Lee, Yong Man Ro

To combat against adversarial attacks, autoencoder structure is widely used to perform denoising which is regarded as gradient masking. In this paper, we revisit the role of autoencoders in adversarial settings. Through …

Adversarial DefenseAdversarial RobustnessDenoising

Revisiting AUC-oriented Adversarial Training with Loss-Agnostic Perturbations

2023-08-10 · TPAMI 2023 8 · Zhiyong Yang, Qianqian Xu, Wenzheng Hou, Shilong Bao 외

The Area Under the ROC curve (AUC) is a popular metric for long-tail classification. Many efforts have been devoted to AUC optimization methods in the past decades. However, little exploration has been done to make them …