paper-with-me

홈 › Papers

You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle

2019-05-02 · NeurIPS 2019 12 · Dinghuai Zhang, Tianyuan Zhang, Yiping Lu, Zhanxing Zhu, Bin Dong

Deep learning achieves state-of-the-art results in many tasks in computer vision and natural language processing. However, recent works have shown that deep networks can be vulnerable to adversarial perturbations, which raised a serious robustness issue of deep networks. Adversarial training, typically formulated as a robust optimization problem, is an effective way of improving the robustness of deep networks. A major drawback of existing adversarial training algorithms is the computational overhead of the generation of adversarial examples, typically far greater than that of the network training. This leads to the unbearable overall computational cost of adversarial training. In this paper, we show that adversarial training can be cast as a discrete time differential game. Through analyzing the Pontryagin's Maximal Principle (PMP) of the problem, we observe that the adversary update is only coupled with the parameters of the first layer of the network. This inspires us to restrict most of the forward and back propagation within the first layer of the network during adversary updates. This effectively reduces the total number of full forward and backward propagation to only one for each group of adversary updates. Therefore, we refer to this algorithm YOPO (You Only Propagate Once). Numerical experiments demonstrate that YOPO can achieve comparable defense accuracy with approximately 1/5 ~ 1/4 GPU time of the projected gradient descent (PGD) algorithm. Our codes are available at https://https://github.com/a1600012888/YOPO-You-Only-Propagate-Once.

📄 PDF Abstract BibTeX arXiv:1905.00877

Code (2)

a1600012888/YOPO-You-Only-Propagate-Once 공식 구현 pytorch
findoctor/YOPO_reproduce pytorch

Tasks

Adversarial DefenseGPU

Similar Papers 제목 키워드 기반

Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustness

2022-02-21 · Beomsu Kim, Junghoon Seo

Adversarial examples, crafted by adding imperceptible perturbations to natural inputs, can easily fool deep neural networks (DNNs). One of the most successful methods for training adversarially robust DNNs is solving a n…

Adversarial Robustness

Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness

2026-01-21 · Yufei Song, Ziqi Zhou, Menghao Deng, Yifan Hu 외 arxiv

Existing segmentation models exhibit significant vulnerability to adversarial attacks.To improve robustness, adversarial training incorporates adversarial examples into model training. However, existing attack methods co…

Semantic Segmentation

Adversarial training for tabular data with attack propagation

2023-07-28 · Tiago Leon Melo, João Bravo, Marco O. P. Sampaio, Paolo Romano 외

Adversarial attacks are a major concern in security-centered applications, where malicious actors continuously try to mislead Machine Learning (ML) models into wrongly classifying fraudulent activity as legitimate, where…

Feature EngineeringFraud Detection

Accelerating Optimization via Differentiable Stopping Time

2025-05-28 · Zhonglin Xie, Yiman Fong, Haoran Yuan, Zaiwen Wen

Optimization is an important module of modern machine learning applications. Tremendous efforts have been made to accelerate optimization algorithms. A common formulation is achieving a lower loss at a given time. This e…

Addressing The False Negative Problem of MRI Reconstruction Networks by Adversarial Attacks and Robust Training

2020-01-25 · MIDL 2019 7 · Kaiyang Cheng, Francesco Calivá, Rutwik Shah, Misung Han 외

Deep learning models have been shown to be successful in accelerating MRI reconstruction, over traditional methods. However, it has been observed that these methods tend to miss rare small features, such as meniscal tear…

DiagnosticMRI ReconstructionSSIM