As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a scalable algorithm for verifying fairness specifications. Our algorithm obtains strong correctness guarantees based on adaptive concentration inequalities; such inequalities enable our algorithm to adaptively take samples until it has enough data to make a decision. We implement our algorithm in a tool called VeriFair, and show that it scales to large machine learning models, including a deep recurrent neural network that is more than five orders of magnitude larger than the largest previously-verified neural network. While our technique only gives probabilistic guarantees due to the use of random samples, we show that we can choose the probability of error to be extremely small.
Whose fairness? Structural concentration in AI bias research
Center for Artificial Intelligence (AI) Research Nepal（人工智能研究尼泊尔中心）；Sharda University（沙达大学）；Shodhguru Innovation and Research Labs（Shodhguru创新与研究实验室）；McGovern Institute for Brain Research（麦戈文脑科学研究院）；Massachusetts Institute of Technology（麻省理工学院）
VeriFlow: Modeling Distributions for Neural Network Verification
Independent Researcher（独立研究者）；TU Dortmund University（图卢兹-多特蒙德大学）；Center for Trustworthy Data Science and Security（可信数据科学与安全中心）；University Alliance Ruhr（鲁尔大学联盟）
TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift
Center for Data Science, New York University, New York, USA（数据科学中心，纽约大学，纽约，美国）；University of New Haven, Connecticut, USA（新罕布什尔大学，康涅狄格，美国）；Queens College, City University of New York, USA（皇后学院，纽约城市大学，美国）
