English
Related papers

Related papers: Disentangling Adversarial Robustness and Generaliz…

200 papers

Adversarial examples pose a unique challenge for deep learning systems. Despite recent advances in both attacks and defenses, there is still a lack of clarity and consensus in the community about the true nature and underlying properties of…

Computer Vision and Pattern Recognition · Computer Science 2021-11-02 Shishira R Maiya , Max Ehrlich , Vatsal Agarwal , Ser-Nam Lim , Tom Goldstein , Abhinav Shrivastava

Adversarial examples are inevitable on the road of pervasive applications of deep neural networks (DNN). Imperceptible perturbations applied on natural samples can lead DNN-based classifiers to output wrong prediction with fair confidence…

Machine Learning · Computer Science 2020-11-04 Tao Bai , Jinqi Luo , Jun Zhao

In this paper, we address the open question: "What do adversarially robust models look at?" Recently, it has been reported in many works that there exists the trade-off between standard accuracy and adversarial robustness. According to…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Takahiro Itazuri , Yoshihiro Fukuhara , Hirokatsu Kataoka , Shigeo Morishima

In adversarial machine learning, there was a common belief that robustness and accuracy hurt each other. The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy. However, the other…

Machine Learning · Computer Science 2021-06-01 Jingfeng Zhang , Jianing Zhu , Gang Niu , Bo Han , Masashi Sugiyama , Mohan Kankanhalli

The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such adversarial behavior, the relationship between the…

Machine Learning · Statistics 2019-06-07 Yujun Shi , Benben Liao , Guangyong Chen , Yun Liu , Ming-Ming Cheng , Jiashi Feng

It has been suggested that adversarial examples cause deep learning models to make incorrect predictions with high confidence. In this work, we take the opposite stance: an overly confident model is more likely to be vulnerable to…

Machine Learning · Computer Science 2018-02-14 Angus Galloway , Graham W. Taylor , Medhat Moussa

Current techniques in machine learning are so far are unable to learn classifiers that are robust to adversarial perturbations. However, they are able to learn non-robust classifiers with very high accuracy, even in the presence of random…

Machine Learning · Computer Science 2019-01-04 Preetum Nakkiran

A necessary characteristic for the deployment of deep learning models in real world applications is resistance to small adversarial perturbations while maintaining accuracy on non-malicious inputs. While robust training provides models that…

Machine Learning · Statistics 2020-02-27 Aditya Saligrama , Guillaume Leclerc

A central challenge of adversarial learning is to interpret the resulting hardened model. In this contribution, we ask how robust generalization can be visually discerned and whether a concise view of the interactions between a hardened…

Machine Learning · Computer Science 2018-05-10 Alex Huang , Abdullah Al-Dujaili , Erik Hemberg , Una-May O'Reilly

Neural networks are known to be highly sensitive to adversarial examples. These may arise due to different factors, such as random initialization, or spurious correlations in the learning problem. To better understand these factors, we…

Machine Learning · Statistics 2022-07-05 Elvis Dohmatob , Alberto Bietti

In this paper, we aim to understand and explain the decisions of deep neural networks by studying the behavior of predicted attributes when adversarial examples are introduced. We study the changes in attributes for clean as well as…

Computer Vision and Pattern Recognition · Computer Science 2019-10-17 Sadaf Gulshad , Zeynep Akata , Jan Hendrik Metzen , Arnold Smeulders

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings…

Machine Learning · Statistics 2019-09-06 Aleksander Madry , Aleksandar Makelov , Ludwig Schmidt , Dimitris Tsipras , Adrian Vladu

Adversarial training (AT) has become the de-facto standard to obtain models robust against adversarial examples. However, AT exhibits severe robust overfitting: cross-entropy loss on adversarial examples, so-called robust loss, decreases…

Machine Learning · Computer Science 2021-10-07 David Stutz , Matthias Hein , Bernt Schiele

Robustness is widely regarded as a fundamental problem in the analysis of machine learning (ML) models. Most often robustness equates with deciding the non-existence of adversarial examples, where adversarial examples denote situations…

Machine Learning · Computer Science 2023-12-19 Yacine Izza , Joao Marques-Silva

The question why deep learning algorithms generalize so well has attracted increasing research interest. However, most of the well-established approaches, such as hypothesis capacity, stability or sparseness, have not provided complete…

Machine Learning · Computer Science 2017-11-07 Tom Zahavy , Bingyi Kang , Alex Sivak , Jiashi Feng , Huan Xu , Shie Mannor

Adversarial training is a widely-applied approach to training deep neural networks to be robust against adversarial perturbation. However, although adversarial training has achieved empirical success in practice, it still remains unclear…

Machine Learning · Computer Science 2025-02-10 Binghui Li , Yuanzhi Li

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this paper, we strive to explore the robust features…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Hong Wang , Yuefan Deng , Shinjae Yoo , Yuewei Lin

Successful deep learning models often involve training neural network architectures that contain more parameters than the number of training samples. Such overparametrized models have been extensively studied in recent years, and the…

Machine Learning · Computer Science 2024-02-02 Hamed Hassani , Adel Javanmard

Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization. However, having a large parameter space is considered one of the main suspects of the neural networks'…

Standard adversarial training approaches suffer from robust overfitting where the robust accuracy decreases when models are adversarially trained for too long. The origin of this problem is still unclear and conflicting explanations have…

Machine Learning · Computer Science 2022-11-28 Muhammad Zaid Hameed , Beat Buesser