中文
相关论文

相关论文: Subspace Adversarial Training

200 篇论文

Adversarial training (AT) aims to improve the robustness of deep learning models by mixing clean data and adversarial examples (AEs). Most existing AT approaches can be grouped into restricted and unrestricted approaches. Restricted AT…

机器学习 · 计算机科学 2020-04-14 Haidong Xie , Xueshuang Xiang , Naijin Liu , Bin Dong

Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast single-step attacks can be used, but this may lead to catastrophic overfitting (CO). This…

To mitigate the susceptibility of neural networks to adversarial attacks, adversarial training has emerged as a prevalent and effective defense strategy. Intrinsically, this countermeasure incurs a trade-off, as it sacrifices the model's…

机器学习 · 计算机科学 2024-09-19 Hanyi Hu , Qiao Han , Kui Chen , Yao Yang

Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face of expensive time and computational cost for calculating…

计算机视觉与模式识别 · 计算机科学 2022-07-13 Xiaojun Jia , Yong Zhang , Baoyuan Wu , Jue Wang , Xiaochun Cao

Deep State Space Models (SSMs) have proven effective in numerous task scenarios but face significant security challenges due to Adversarial Perturbations (APs) in real-world deployments. Adversarial Training (AT) is a mainstream approach to…

机器学习 · 计算机科学 2024-10-10 Biqing Qi , Yang Luo , Junqi Gao , Pengfei Li , Kai Tian , Zhiyuan Ma , Bowen Zhou

Recent improvements in deep learning models and their practical applications have raised concerns about the robustness of these models against adversarial examples. Adversarial training (AT) has been shown effective to reach a robust model…

机器学习 · 计算机科学 2021-03-30 Mohammad Azizmalayeri , Mohammad Hossein Rohban

Adversarial training (AT) is proved to reliably improve network's robustness against adversarial data. However, current AT with a pre-specified perturbation budget has limitations in learning a robust network. Firstly, applying a…

机器学习 · 计算机科学 2022-10-05 Chaojian Yu , Dawei Zhou , Li Shen , Jun Yu , Bo Han , Mingming Gong , Nannan Wang , Tongliang Liu

In this technical report, we evaluate the adversarial robustness of a very recent method called "Geometry-aware Instance-reweighted Adversarial Training"[7]. GAIRAT reports state-of-the-art results on defenses to adversarial attacks on the…

机器学习 · 计算机科学 2021-03-08 Dorjan Hitaj , Giulio Pagnotta , Iacopo Masi , Luigi V. Mancini

It is well known that adversarial attacks can fool deep neural networks with imperceptible perturbations. Although adversarial training significantly improves model robustness, failure cases of defense still broadly exist. In this work, we…

机器学习 · 计算机科学 2021-06-10 Boxi Wu , Heng Pan , Li Shen , Jindong Gu , Shuai Zhao , Zhifeng Li , Deng Cai , Xiaofei He , Wei Liu

While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models. To mitigate the costs, we propose Guided…

计算机视觉与模式识别 · 计算机科学 2023-05-26 Salah Ghamizi , Jingfeng Zhang , Maxime Cordy , Mike Papadakis , Masashi Sugiyama , Yves Le Traon

Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…

计算机视觉与模式识别 · 计算机科学 2024-08-15 Lin Li , Jianing Qiu , Michael Spratling

Adversarial training (AT) is a prominent technique employed by deep learning models to defend against adversarial attacks, and to some extent, enhance model robustness. However, there are three main drawbacks of the existing AT-based…

图像与视频处理 · 电气工程与系统科学 2026-03-31 X. Peng , D. Zhou , G. Sun , J. Shi , L. Wu

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set linguistic knowledge and assume that the synonym candidates…

计算与语言 · 计算机科学 2024-02-28 Yichen Yang , Xin Liu , Kun He

Deep learning models have achieved state-of-the-art performances in various domains, while they are vulnerable to the inputs with well-crafted but small perturbations, which are named after adversarial examples (AEs). Among many strategies…

计算机视觉与模式识别 · 计算机科学 2023-10-11 Huihui Gong

Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite contributing…

机器学习 · 计算机科学 2025-12-29 Youran Ye , Dejin Wang , Ajinkya Bhandare

Despite the fact that adversarial training has become the de facto method for improving the robustness of deep neural networks, it is well-known that vanilla adversarial training suffers from daunting robust overfitting, resulting in…

机器学习 · 计算机科学 2024-02-06 Tianjin Huang , Shiwei Liu , Tianlong Chen , Meng Fang , Li Shen , Vlaod Menkovski , Lu Yin , Yulong Pei , Mykola Pechenizkiy

Deep Neural Networks (DNN) have been shown to be vulnerable to adversarial examples. Adversarial training (AT) is a popular and effective strategy to defend against adversarial attacks. Recent works (Benz et al., 2020; Xu et al., 2021; Tian…

机器学习 · 计算机科学 2023-02-09 Boqi Li , Weiwei Liu

Current deep neural networks (DNNs) are vulnerable to adversarial attacks, where adversarial perturbations to the inputs can change or manipulate classification. To defend against such attacks, an effective and popular approach, known as…

机器学习 · 计算机科学 2022-09-08 Gaoyuan Zhang , Songtao Lu , Yihua Zhang , Xiangyi Chen , Pin-Yu Chen , Quanfu Fan , Lee Martie , Lior Horesh , Mingyi Hong , Sijia Liu

Adversarial training is widely used to improve the robustness of deep neural networks to adversarial attack. However, adversarial training is prone to overfitting, and the cause is far from clear. This work sheds light on the mechanisms…

机器学习 · 计算机科学 2022-12-12 Lin Li , Michael Spratling

Adversarial training enhances neural network robustness but suffers from a tendency to overfit and increased generalization errors on clean data. This work introduces CLAT, an innovative approach that mitigates adversarial overfitting by…

机器学习 · 计算机科学 2024-12-25 Bhavna Gopal , Huanrui Yang , Jingyang Zhang , Mark Horton , Yiran Chen