English
Related papers

Related papers: The Interplay between Distribution Parameters and …

200 papers

Most previous works usually explained adversarial examples from several specific perspectives, lacking relatively integral comprehension about this problem. In this paper, we present a systematic study on adversarial examples from three…

Machine Learning · Computer Science 2019-03-01 Ke Sun , Zhanxing Zhu , Zhouchen Lin

Robustness is a key requirement for widespread deployment of machine learning algorithms, and has received much attention in both statistics and computer science. We study a natural model of robustness for high-dimensional statistical…

Machine Learning · Computer Science 2020-06-03 Pranjal Awasthi , Xue Chen , Aravindan Vijayaraghavan

Bias in classifiers is a severe issue of modern deep learning methods, especially for their application in safety- and security-critical areas. Often, the bias of a classifier is a direct consequence of a bias in the training dataset,…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Christian Reimers , Paul Bodesheim , Jakob Runge , Joachim Denzler

Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing…

Machine Learning · Computer Science 2025-09-29 Natalie S. Frank

Training and evaluation of fair classifiers is a challenging problem. This is partly due to the fact that most fairness metrics of interest depend on both the sensitive attribute information and label information of the data points. In many…

Machine Learning · Computer Science 2021-02-18 Pranjal Awasthi , Alex Beutel , Matthaeus Kleindessner , Jamie Morgenstern , Xuezhi Wang

Deep Learning models are vulnerable to adversarial examples, i.e.\ images obtained via deliberate imperceptible perturbations, such that the model misclassifies them with high confidence. However, class confidence by itself is an incomplete…

Machine Learning · Statistics 2017-11-23 Ambrish Rawat , Martin Wistuba , Maria-Irina Nicolae

In this paper we aim to explore the general robustness of neural network classifiers by utilizing adversarial as well as natural perturbations. Different from previous works which mainly focus on studying the robustness of neural networks…

Computer Vision and Pattern Recognition · Computer Science 2020-10-06 Sadaf Gulshad , Jan Hendrik Metzen , Arnold Smeulders

We study the extent to which standard machine learning algorithms rely on exchangeability and independence of data by introducing a monotone adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d.…

Machine Learning · Computer Science 2026-01-06 Kasper Green Larsen , Chirag Pabbaraju , Abhishek Shetty

Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Yanghao Zhang , Tianle Zhang , Ronghui Mu , Xiaowei Huang , Wenjie Ruan

The susceptibility of modern machine learning classifiers to adversarial examples has motivated theoretical results suggesting that these might be unavoidable. However, these results can be too general to be applicable to natural data…

Machine Learning · Computer Science 2024-05-28 Ambar Pal , Jeremias Sulam , René Vidal

Modern machine learning algorithms perform poorly on adversarially manipulated data. Adversarial risk quantifies the error of classifiers in adversarial settings; adversarial classifiers minimize adversarial risk. In this paper, we analyze…

Machine Learning · Computer Science 2020-12-24 Muni Sreenivas Pydi , Varun Jog

The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem. Existing methodologies aimed to enhance robust fairness by sacrificing the model's…

Machine Learning · Computer Science 2024-01-24 Hyungyu Lee , Saehyung Lee , Hyemi Jang , Junsung Park , Ho Bae , Sungroh Yoon

Machine learning models are vulnerable to adversarial examples: minor perturbations to input samples intended to deliberately cause misclassification. While an obvious security threat, adversarial examples yield as well insights about the…

Cryptography and Security · Computer Science 2019-11-19 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes

We derive a fundamental trade-off between standard and adversarial risk in a rather general situation that formalizes the following simple intuition: "If no (nearly) optimal predictor is smooth, adversarial robustness comes at the cost of…

Machine Learning · Statistics 2025-07-01 Sohail Bahmani

Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute.…

Machine Learning · Computer Science 2022-02-07 Han Zhao , Geoffrey J. Gordon

In this paper, we propose a new framework to detect adversarial examples motivated by the observations that random components can improve the smoothness of predictors and make it easier to simulate the output distribution of a deep neural…

Machine Learning · Statistics 2024-02-26 Yao Li , Tongyi Tang , Cho-Jui Hsieh , Thomas C. M. Lee

We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one predictors, bounds relating the adversarial convex loss to…

Machine Learning · Computer Science 2024-04-30 Justin D. Li , Matus Telgarsky

While adversarial training methods have significantly improved the robustness of deep neural networks against norm-bounded adversarial perturbations, the generalization gap between their performance on training and test data is considerably…

Machine Learning · Computer Science 2025-01-08 Xiwei Cheng , Kexin Fu , Farzan Farnia

Machine learning models are vulnerable to Adversarial Examples: minor perturbations to input samples intended to deliberately cause misclassification. Current defenses against adversarial examples, especially for Deep Neural Networks (DNN),…

Cryptography and Security · Computer Science 2019-01-04 Kathrin Grosse , David Pfaff , Michael Thomas Smith , Michael Backes

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning…

Machine Learning · Computer Science 2022-06-24 Haojing Shen , Sihong Chen , Ran Wang , Xizhao Wang