相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Tao Zhang et al.
Summary: As deep learning models mature, finding the ideal tradeoff between accuracy, fairness, and privacy is critical. Privacy and fairness can affect the accuracy of models, so balancing these needs is important. By implementing differentially private stochastic gradient descent (DP-SGD) in deep neural network models, privacy and fairness can be indirectly managed. The number of training epochs plays a central role in striking a balance between accuracy, fairness, and privacy. Based on this observation, two early stopping criteria are designed to help analysts achieve their ideal tradeoff.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Eliane Roosli et al.
Summary: As artificial intelligence continues to improve the quality of care for some patients, there is a risk of reinforcing health disparities faced by minority populations. This study highlights the need for empirical evaluation studies and the use of fairness and performance assessment frameworks to address bias and fairness concerns in risk prediction models.
Article
Computer Science, Artificial Intelligence
Tai Le Quy et al.
Summary: As decision-making increasingly relies on machine learning and big data, fairness in data-driven artificial intelligence systems is receiving more attention. This paper provides an overview of real-world datasets used for fairness-aware machine learning and analyzes the relationships between different attributes, particularly those related to fairness.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2022)
Review
Computer Science, Information Systems
Alycia N. Carey et al.
Summary: This article introduces different methods to measure the causal fairness of machine learning models, highlighting the lack of literature that combines causality-based fairness notions with social sciences such as philosophy, sociology, and law. The authors aim to bridge this gap by discussing the thoughts and discussions of causality-based fairness notions produced by both social and formal sciences, providing a deeper understanding of the alignment between these notions and important humanistic values. The article also explores criticisms of current approaches to causality-based fair machine learning from sociological and technical perspectives, ultimately aiming to improve methods and metrics to serve oppressed and marginalized populations better.
FRONTIERS IN BIG DATA
(2022)
Article
Engineering, Electrical & Electronic
Bernhard Schoelkopf et al.
Summary: The fields of machine learning and graphical causality have started to influence each other and show interest in benefiting from each other's advancements. Understanding fundamental concepts of causal inference, and relating them to key issues in machine learning, can help enhance modern machine learning research. A central problem in the intersection of AI and causality is the learning of causal representations, which involves discovering high-level causal variables from low-level observations.
PROCEEDINGS OF THE IEEE
(2021)
Article
Computer Science, Theory & Methods
Ninareh Mehrabi et al.
Summary: With the widespread use of AI systems in everyday life, fairness in design has become crucial. Researchers have developed methods to address biases in different subdomains and established a taxonomy for fairness definitions. Existing work shows biases in AI applications, and researchers are working on solutions to mitigate these problems.
ACM COMPUTING SURVEYS
(2021)
Proceedings Paper
Computer Science, Information Systems
Md Tamjid Hossain et al.
Summary: The paper analyzes the adversarial learning process in an FL setting, illustrating a method to conduct stealthy and persistent model poisoning attacks using differential noise. The empirical analysis demonstrates the effectiveness of this attack. Additionally, a novel reinforcement learning-based defense strategy is proposed to counter model poisoning attacks.
2021 17TH INTERNATIONAL CONFERENCE ON MOBILITY, SENSING AND NETWORKING (MSN 2021)
(2021)
Proceedings Paper
Computer Science, Information Systems
Hongyan Chang et al.
Summary: Algorithmic fairness and privacy are crucial pillars of trustworthy machine learning, but pursuing fairness may lead to privacy risks. Research shows that achieving fairness comes at the cost of privacy, especially for unprivileged subgroups.
2021 IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY (EUROS&P 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Qi Tian et al.
Summary: This paper analyzes the class-wise robustness in adversarial training, revealing significant differences in robustness among classes. A new attack method called Temperature-PGD attack is proposed to increase attack effectiveness, and modifications in training and inference phases are made to improve the robustness of the most vulnerable class and reduce the disparities in class-wise robustness.
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING
(2021)
Article
Social Sciences, Mathematical Methods
Richard Berk et al.
Summary: This article clarifies the trade-offs between accuracy and fairness in criminal justice risk assessments, highlighting at least six kinds of fairness which may be incompatible with each other and with accuracy. The differences in base rates across legally protected groups present a major complication in practice, requiring consideration of challenging trade-offs.
SOCIOLOGICAL METHODS & RESEARCH
(2021)
Article
Computer Science, Theory & Methods
Emad Alsuwat et al.
INTERNATIONAL JOURNAL OF GENERAL SYSTEMS
(2020)
Review
Computer Science, Artificial Intelligence
Maoguo Gong et al.
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE
(2020)
Proceedings Paper
Computer Science, Information Systems
Jairo Giraldo et al.
27TH ANNUAL NETWORK AND DISTRIBUTED SYSTEM SECURITY SYMPOSIUM (NDSS 2020)
(2020)
Article
Computer Science, Information Systems
Bulent Yener et al.
IEEE SECURITY & PRIVACY
(2019)
Proceedings Paper
Computer Science, Theory & Methods
Sorelle A. Friedler et al.
FAT*'19: PROCEEDINGS OF THE 2019 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY
(2019)
Proceedings Paper
Computer Science, Information Systems
Liwei Song et al.
PROCEEDINGS OF THE 2019 ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY (CCS'19)
(2019)
Proceedings Paper
Computer Science, Information Systems
Brianna Maze et al.
2018 INTERNATIONAL CONFERENCE ON BIOMETRICS (ICB)
(2018)
Proceedings Paper
Computer Science, Software Engineering
Sahil Verma et al.
2018 IEEE/ACM INTERNATIONAL WORKSHOP ON SOFTWARE FAIRNESS (FAIRWARE 2018)
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Siyue Wang et al.
2018 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER-AIDED DESIGN (ICCAD) DIGEST OF TECHNICAL PAPERS
(2018)
Proceedings Paper
Computer Science, Theory & Methods
Depeng Xu et al.
2017 1ST IEEE SYMPOSIUM ON PRIVACY-AWARE COMPUTING (PAC)
(2017)
Proceedings Paper
Computer Science, Theory & Methods
Marc Andrysco et al.
2015 IEEE SYMPOSIUM ON SECURITY AND PRIVACY SP 2015
(2015)
Proceedings Paper
Computer Science, Theory & Methods
Raef Bassily et al.
2014 55TH ANNUAL IEEE SYMPOSIUM ON FOUNDATIONS OF COMPUTER SCIENCE (FOCS 2014)
(2014)
Article
Computer Science, Theory & Methods
Cynthia Dwork et al.
FOUNDATIONS AND TRENDS IN THEORETICAL COMPUTER SCIENCE
(2013)
Article
Psychology, Experimental
Ilya Shpitser
Article
Computer Science, Artificial Intelligence
Huan Xu et al.
