中文
相关论文

相关论文: To be Robust and to be Fair: Aligning Fairness wit…

200 篇论文

Optimizing prediction accuracy can come at the expense of fairness. Towards minimizing discrimination against a group, fair machine learning algorithms strive to equalize the behavior of a model across different groups, by imposing a…

机器学习 · 统计学 2020-06-17 Hongyan Chang , Ta Duy Nguyen , Sasi Kumar Murakonda , Ehsan Kazemi , Reza Shokri

Adversarial training (AT) methods are effective against adversarial attacks, yet they introduce severe disparity of accuracy and robustness between different classes, known as the robust fairness problem. Previously proposed Fair Robust…

机器学习 · 计算机科学 2022-09-19 Chunyu Sun , Chenye Xu , Chengyuan Yao , Siyuan Liang , Yichao Wu , Ding Liang , XiangLong Liu , Aishan Liu

Adversarial training is an effective learning technique to improve the robustness of deep neural networks. In this study, the influence of adversarial training on deep learning models in terms of fairness, robustness, and generalization is…

机器学习 · 计算机科学 2023-05-19 Xiaoling Zhou , Nan Yang , Ou Wu

The remarkable performance of deep learning models and their applications in consequential domains (e.g., facial recognition) introduces important challenges at the intersection of equity and security. Fairness and robustness are two…

机器学习 · 计算机科学 2022-11-24 Cuong Tran , Keyu Zhu , Ferdinando Fioretto , Pascal Van Hentenryck

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…

机器学习 · 计算机科学 2024-01-24 Hyungyu Lee , Saehyung Lee , Hyemi Jang , Junsung Park , Ho Bae , Sungroh Yoon

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that…

机器学习 · 计算机科学 2021-07-27 Ali Rahmati , Seyed-Mohsen Moosavi-Dezfooli , Huaiyu Dai

Adversarial training algorithms have been proved to be reliable to improve machine learning models' robustness against adversarial examples. However, we find that adversarial training algorithms tend to introduce severe disparity of…

机器学习 · 计算机科学 2021-05-20 Han Xu , Xiaorui Liu , Yaxin Li , Anil K. Jain , Jiliang Tang

Convolutional neural networks (CNNs) have made significant advancement, however, they are widely known to be vulnerable to adversarial attacks. Adversarial training is the most widely used technique for improving adversarial robustness to…

机器学习 · 计算机科学 2021-10-12 Philipp Benz , Chaoning Zhang , Adil Karjauv , In So Kweon

Adversarial robustness, which primarily comprises sensitivity-based robustness and spatial robustness, plays an integral part in achieving robust generalization. In this paper, we endeavor to design strategies to achieve universal…

机器学习 · 计算机科学 2024-06-25 Ke Sun , Mingjie Li , Zhouchen Lin

Adversarial training (i.e., training on adversarially perturbed input data) is a well-studied method for making neural networks robust to potential adversarial attacks during inference. However, the improved robustness does not come for…

机器人学 · 计算机科学 2023-01-27 Mathias Lechner , Alexander Amini , Daniela Rus , Thomas A. Henzinger

With the introduction of machine learning in high-stakes decision making, ensuring algorithmic fairness has become an increasingly important problem to solve. In response to this, many mathematical definitions of fairness have been…

机器学习 · 计算机科学 2024-06-04 Edward Small , Wei Shao , Zeliang Zhang , Peihan Liu , Jeffrey Chan , Kacper Sokol , Flora Salim

Despite the essential need for comprehensive considerations in responsible AI, factors like robustness, fairness, and causality are often studied in isolation. Adversarial perturbation, used to identify vulnerabilities in models, and…

机器学习 · 计算机科学 2024-02-07 Ahmad-Reza Ehyaei , Golnoosh Farnadi , Samira Samadi

Adversarial training is one of the predominant techniques for training classifiers that are robust to adversarial attacks. Recent work, however has found that adversarial training, which makes the overall classifier robust, it does not…

机器学习 · 计算机科学 2024-11-22 Meiyu Zhong , Ravi Tandon

Deep neural networks are susceptible to adversarial attacks and common corruptions, which undermine their robustness. In order to enhance model resilience against such challenges, Adversarial Training (AT) has emerged as a prominent…

机器学习 · 计算机科学 2025-06-17 Tejaswini Medi , Steffen Jung , Margret Keuper

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…

计算机视觉与模式识别 · 计算机科学 2024-03-29 Yanghao Zhang , Tianle Zhang , Ronghui Mu , Xiaowei Huang , Wenjie Ruan

The reliability of a learning model is key to the successful deployment of machine learning in various applications. However, it is difficult to describe the phenomenon due to the complicated nature of the problems in machine learning. It…

机器学习 · 计算机科学 2025-05-27 Ramin Barati , Reza Safabakhsh , Mohammad Rahmati

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…

机器学习 · 计算机科学 2021-06-01 Jingfeng Zhang , Jianing Zhu , Gang Niu , Bo Han , Masashi Sugiyama , Mohan Kankanhalli

A small but growing body of work has shown that machine learning models which better align with human vision have also exhibited higher robustness to adversarial examples, raising the question: can human-like perception make models more…

计算机视觉与模式识别 · 计算机科学 2025-07-15 Blaine Hoak , Kunyang Li , Patrick McDaniel

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve robustness to worst-case distribution shifts caused by…

计算机视觉与模式识别 · 计算机科学 2025-03-21 Fatemeh Amerehi , Patrick Healy

In this paper, we take a first step towards answering the question of how to design fair machine learning algorithms that are robust to adversarial attacks. Using a minimax framework, we aim to design an adversarially robust fair regression…

密码学与安全 · 计算机科学 2022-11-09 Yulu Jin , Lifeng Lai
‹ 上一页 1 2 3 10 下一页 ›