As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these applications before deployment. Existing fairness testing methods suffer from the following limitations: 1) applicability, i.e., they are only applicable for structured data or text without handling the high-dimensional and abstract domain sampling in the semantic level for image classification applications; 2) functionality, i.e., they generate unfair samples without providing testing criterion to characterize the model's fairness adequacy. To fill the gap, we propose DeepFAIT, a systematic fairness testing framework specifically designed for deep image classification applications. DeepFAIT consists of several important components enabling effective fairness testing of deep image classification applications: 1) a neuron selection strategy to identify the fairness-related neurons; 2) a set of multi-granularity adequacy metrics to evaluate the model's fairness; 3) a test selection algorithm for fixing the fairness issues efficiently. We have conducted experiments on widely adopted large-scale face recognition applications, i.e., VGGFace and FairFace. The experimental results confirm that our approach can effectively identify the fairness-related neurons, characterize the model's fairness, and select the most valuable test cases to mitigate the model's fairness issues.
Wasserstein projection distance for fairness testing of regression models
Department of Computer Science, University of British Columbia（计算机科学系，不列颠哥伦比亚大学）；Department of Pathology and Laboratory Medicine, University of British Columbia（病理学与实验室医学系，不列颠哥伦比亚大学）；Department of Statistics, University of British Columbia（统计学系，不列颠哥伦比亚大学）；BC Cancer Research, Part of Provincial Health Care Authority（BC癌症研究，省卫生保健机构的一部分）；Department of Mathematics, University of British Columbia（数学系，不列颠哥伦比亚大学）
The applications of Artificial Intelligence (AI) surround decisions on increasingly many aspects of human lives. Society responds by imposing legal and social expectations for the accountability of such automated decision systems (ADSs). Fairness, a fundamental constituent of AI accountability, is concerned with just treatment of individuals and sensitive groups (e.g., based on sex, race). While many studies focus on fair learning and fairness testing for the classification tasks, the literature is rather limited on how to examine fairness in regression tasks. This work presents error parity a…
Machine learning models are vulnerable to biases that result in unfair treatment of individuals from different populations. Recent work that aims to test a model's fairness at the individual level either relies on domain knowledge to choose metrics, or on input transformations that risk generating out-of-domain samples. We describe a new approach for testing individual fairness that does not have either requirement. We propose a novel criterion for evaluating individual fairness and develop a practical testing method based on this criterion which we call fAux (pronounced fox). This is based on…
The fairness characteristic is a critical attribute of trusted AI systems. A plethora of research has proposed diverse methods for individual fairness testing. However, they are suffering from three major limitations, i.e., low efficiency, low effectiveness, and model-specificity. This work proposes ExpGA, an explanationguided fairness testing approach through a genetic algorithm (GA). ExpGA employs the explanation results generated by interpretable methods to collect high-quality initial seeds, which are prone to derive discriminatory samples by slightly modifying feature values. ExpGA then a…
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg（卢森堡大学安全、可靠性与信任跨学科中心）；Singapore University of Technology and Design（新加坡科技设计大学）
Software often produces biased outputs. In particular, machine learning (ML) based software are known to produce erroneous predictions when processing discriminatory inputs. Such unfair program behavior can be caused by societal bias. In the last few years, Amazon, Microsoft and Google have provided software services that produce unfair outputs, mostly due to societal bias (e.g. gender or race). In such events, developers are saddled with the task of conducting fairness testing. Fairness testing is challenging; developers are tasked with generating discriminatory inputs that reveal and explain…
Surprise Adequacy (SA) is one of the emerging and most promising adequacy criteria for Deep Learning (DL) testing. As an adequacy criterion, it has been used to assess the strength of DL test suites. In addition, it has also been used to find inputs to a Deep Neural Network (DNN) which were not sufficiently represented in the training data, or to select samples for DNN retraining. However, computation of the SA metric for a test suite can be prohibitively expensive, as it involves a quadratic number of distance calculations. Hence, we developed and released a performance-optimized, but functio…
North Carolina State University（北卡罗来纳州立大学）；Indian Institute of Management（印度管理学院）
Machine learning has become more important in real-life decision-making but people are concerned about the ethical problems it may bring when used improperly. Recent work brings the discussion of machine learning fairness into the causal framework and elaborates on the concept of Counterfactual Fairness. In this paper, we develop the Fair Learning through dAta Preprocessing (FLAP) algorithm to learn counterfactually fair decisions from biased training data and formalize the conditions where different data preprocessing procedures should be used to guarantee counterfactual fairness. We also sho…
University of Arkansas（阿肯色大学）；University of Illinois（伊利诺伊大学）
Federated learning is an emerging framework that builds centralized machine learning models with training data distributed across multiple devices. Most of the previous works about federated learning focus on the privacy protection and communication cost reduction. However, how to achieve fairness in federated learning is under-explored and challenging especially when testing data distribution is different from training distribution or even unknown. Introducing simple fairness constraints on the centralized model cannot achieve model fairness on unknown testing data. In this paper, we develop …
Zhejiang University of Technology（浙江工业大学）；Zhejiang University（浙江大学）；Huawei International Pte. Ltd.（华为国际有限公司）；National University of Defense Technology（国防科技大学）
Deep neural networks (DNNs) have demonstrated their outperformance in various domains. However, it raises a social concern whether DNNs can produce reliable and fair decisions especially when they are applied to sensitive domains involving valuable resource allocation, such as education, loan, and employment. It is crucial to conduct fairness testing before DNNs are reliably deployed to such sensitive domains, i.e., generating as many instances as possible to uncover fairness violations. However, the existing testing methods are still limited from three aspects: interpretability, performance, …
Stanford University（斯坦福大学）；Singapore University of Technology and Design（新加坡科技设计大学）；VinAI Research（VinAI研究院）
We present a statistical testing framework to detect if a given machine learning classifier fails to satisfy a wide range of group fairness notions. The proposed test is a flexible, interpretable, and statistically rigorous tool for auditing whether exhibited biases are intrinsic to the algorithm or due to the randomness in the data. The statistical challenges, which may arise from multiple impact criteria that define group fairness and which are discontinuous on model parameters, are conveniently tackled by projecting the empirical measure onto the set of group-fair probability models using o…
Microsoft Research Lab Asia（微软亚洲研究院）；University College London（伦敦大学学院）；The University of Newcastle（纽卡斯尔大学）
Fairness testing aims at mitigating unintended discrimination in the decision-making process of data-driven AI systems. Individual discrimination may occur when an AI model makes different decisions for two distinct individuals who are distinguishable solely according to protected attributes, such as age and race. Such instances reveal biased AI behaviour, and are called Individual Discriminatory Instances (IDIs). In this paper, we propose an approach for the selection of the initial seeds to generate IDIs for fairness testing. Previous studies mainly used random initial seeds to this end. How…
Zhejiang University（浙江大学）；Singapore Management University（新加坡管理大学）；Huawei International Pte. Ltd.（华为国际私人有限公司）；National University of Singapore（新加坡国立大学）
Although deep learning has demonstrated astonishing performance in many applications, there are still concerns about its dependability. One desirable property of deep learning applications with societal impact is fairness (i.e., non-discrimination). Unfortunately, discrimination might be intrinsically embedded into the models due to the discrimination in the training data. As a countermeasure, fairness testing systemically identifies discriminatory samples, which can be used to retrain the model and improve the model's fairness. Existing fairness testing approaches however have two major limit…
Testing machine learning software for ethical bias has become a pressing current concern. In response, recent research has proposed a plethora of new fairness metrics, for example, the dozens of fairness metrics in the IBM AIF360 toolkit. This raises the question: How can any fairness tool satisfy such a diverse range of goals? While we cannot completely simplify the task of fairness testing, we can certainly reduce the problem. This paper shows that many of those fairness metrics effectively measure the same thing. Based on experiments using seven real-world datasets, we find that (a) 26 clas…
We present FlipTest, a black-box technique for uncovering discrimination in classifiers. FlipTest is motivated by the intuitive question: had an individual been of a different protected status, would the model have treated them differently? Rather than relying on causal information to answer this question, FlipTest leverages optimal transport to match individuals in different protected groups, creating similar pairs of in-distribution samples. We show how to use these instances to detect discrimination by constructing a "flipset": the set of individuals whose classifier output changes post-tra…
University of Massachusetts, Amherst（马萨诸塞大学阿默斯特分校）
This paper defines software fairness and discrimination and develops a testing-based method for measuring if and how much software discriminates, focusing on causality in discriminatory behavior. Evidence of software discrimination has been found in modern software systems that recommend criminal sentences, grant access to financial products, and determine who is allowed to participate in promotions. Our approach, Themis, generates efficient test suites to measure discrimination. Given a schema describing valid system inputs, Themis generates discrimination tests automatically and does not req…
Singapore University of Technology and Design（新加坡科技设计大学）
Automatic Speech Recognition (ASR) systems have become ubiquitous. They can be found in a variety of form factors and are increasingly important in our daily lives. As such, ensuring that these systems are equitable to different subgroups of the population is crucial. In this paper, we introduce, AequeVox, an automated testing framework for evaluating the fairness of ASR systems. AequeVox simulates different environments to assess the effectiveness of ASR systems for different populations. In addition, we investigate whether the chosen simulations are comprehensible to humans. We further propo…
Clotho: Measuring Task-Specific Pre-Generation Test Adequacy for LLM Inputs
Korea Advanced Institute of Science and Technology（韩国科学技术院）；Chalmers University of Technology Gothenburg Sweden（楚德大学哥德堡瑞典）；Chalmers University of Technology（楚德大学）
IBM Research（IBM研究院）；Carnegie Mellon University（卡内基梅隆大学）
A trade-off between accuracy and fairness is almost taken as a given in the existing literature on fairness in machine learning. Yet, it is not preordained that accuracy should decrease with increased fairness. Novel to this work, we examine fair classification through the lens of mismatched hypothesis testing: trying to find a classifier that distinguishes between two ideal distributions when given two mismatched distributions that are biased. Using Chernoff information, a tool in information theory, we theoretically demonstrate that, contrary to popular belief, there always exist ideal distr…
Singapore Univ. of Tech. and Design（新加坡科技设计大学）；BITS Pilani（皮拉尼博拉理工学院）
Fairness is a critical trait in decision making. As machine-learning models are increasingly being used in sensitive application domains (e.g. education and employment) for decision making, it is crucial that the decisions computed by such models are free of unintended bias. But how can we automatically validate the fairness of arbitrary machine-learning models? For a given machine-learning model and a set of sensitive input parameters, our AEQUITAS approach automatically discovers discriminatory inputs that highlight fairness violation. At the core of AEQUITAS are three novel strategies to em…
University of Texas at El Paso（德克萨斯大学埃尔帕索分校）；Virginia Tech（弗吉尼亚理工大学）；Austin Peay State University（奥斯汀佩伊州立大学）
In this research, we focus on the usage of adversarial sampling to test for the fairness in the prediction of deep neural network model across different classes of image in a given dataset. While several framework had been proposed to ensure robustness of machine learning model against adversarial attack, some of which includes adversarial training algorithm. There is still the pitfall that adversarial training algorithm tends to cause disparity in accuracy and robustness among different group. Our research is aimed at using adversarial sampling to test for fairness in the prediction of deep n…
Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）
Testing Deep Neural Network (DNN) models has become more important than ever with the increasing usage of DNN models in safety-critical domains such as autonomous cars. The traditional approach of testing DNNs is to create a test set, which is a random subset of the dataset about the problem of interest. This kind of approach is not enough for testing most of the real-world scenarios since these traditional test sets do not include corner cases, while a corner case input is generally considered to introduce erroneous behaviors. Recent works on adversarial input generation, data augmentation, a…
A semantic mutation metric for metamorphic relation adequacy in scientific computing programs
School of Computing, University of South China（南华大学计算机学院）；Hunan Engineering Research Center of Software Evaluation and Testing for Intellectual Equipment（湖南软件测评与智能设备工程研究中心）；CNNC Key Laboratory on High Trusted Computing（中核集团高可信计算重点实验室）
Testing autonomous vehicles and AI: perspectives and challenges from cybersecurity, transparency, robustness and fairness
European Commission, Joint Research Centre（欧盟委员会联合研究中心）；University of Alcalá（阿尔卡拉大学）；EPFL - Swiss Federal Institute of Technology（瑞士洛桑联邦理工学院）；University of Oxford（牛津大学）；BASt - German Federal Highway Research Institute（德国联邦公路研究所）；Reed Mobility（里德移动公司）
Harbin Institute of Technology（哈尔滨工业大学）；Carnegie Mellon University（卡内基梅隆大学）；Nanyang Technological University（南洋理工大学）；Kyushu University（九州大学）；University of Illinois at Urbana–Champaign（伊利诺伊大学厄巴纳-香槟分校）；Monash University（莫纳什大学）
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good acc…
Discrimination has been shown in many machine learning applications, which calls for sufficient fairness testing before their deployment in ethic-relevant domains such as face recognition, medical diagnosis and criminal sentence. Existing fairness testing approaches are mostly designed for identifying individual discrimination, i.e., discrimination against individuals. Yet, as another widely concerning type of discrimination, testing against group discrimination, mostly hidden, is much less studied. To address the gap, in this work, we propose TESTSGD, an interpretable testing approach which s…
Quantitative definitions of what is unfair and what is fair have been introduced in multiple disciplines for well over 50 years, including in education, hiring, and machine learning. We trace how the notion of fairness has been defined within the testing communities of education and hiring over the past half century, exploring the cultural and social context in which different fairness definitions have emerged. In some cases, earlier definitions of fairness are similar or identical to definitions of fairness in current machine learning research, and foreshadow current formal work. In other cas…
University of Texas, Austin（德克萨斯大学奥斯汀分校）；University of Manchester（曼彻斯特大学）；KBR（KBR公司）；Princeton University（普林斯顿大学）；Palo Alto High School（帕洛阿尔托高中）
Deep neural network (DNN) models, including those used in safety-critical domains, need to be thoroughly tested to ensure that they can reliably perform well in different scenarios. In this article, we provide an overview of structural coverage metrics for testing DNN models, including neuron coverage (NC), k-multisection neuron coverage (kMNC), top-k neuron coverage (TKNC), neuron boundary coverage (NBC), strong neuron activation coverage (SNAC) and modified condition/decision coverage (MC/DC). We evaluate the metrics on realistic DNN models used for perception tasks (including LeNet-1, LeNet…
Surprise Adequacy (SA) has been widely studied as a test adequacy metric that can effectively guide software engineers towards inputs that are more likely to reveal unexpected behaviour of Deep Neural Networks (DNNs). Intuitively, SA is an out-of-distribution metric that quantifies the dissimilarity between the given input and the training data: if a new input is very different from those seen during training, the DNN is more likely to behave unexpectedly against the input. While SA has been widely adopted as a test prioritization method, its major weakness is the fact that the computation of …
Carnegie Mellon University（卡内基梅隆大学）；University of Minnesota（明尼苏达大学）
Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Most existing algorithms, however, are agnostic to the sources of the observed unfairness. As a result, the literature currently lacks guiding frameworks to specify conditions under which each algorithmic intervention can potentially alleviate the underpinning cause of unfairness. To close this gap, we scrutinize the underlying biases (e.g., in the training data or design choices) that cause observational unfairness. W…
The increasing inclusion of Deep Learning (DL) models in safety-critical systems such as autonomous vehicles have led to the development of multiple model-based DL testing techniques. One common denominator of these testing techniques is the automated generation of test cases, e.g., new inputs transformed from the original training data with the aim to optimize some test adequacy criteria. So far, the effectiveness of these approaches has been hindered by their reliance on random fuzzing or transformations that do not always produce test cases with a good diversity. To overcome these limitatio…
University of York（约克大学）；MPI-SWS（马克斯·普朗克软件系统研究所）；Bogazici University（博阿齐奇大学）
Deep Learning (DL) systems are key enablers for engineering intelligent applications due to their ability to solve complex tasks such as image recognition and machine translation. Nevertheless, using DL systems in safety- and security-critical applications requires to provide testing evidence for their dependable operation. Recent research in this direction focuses on adapting testing criteria from traditional software engineering as a means of increasing confidence for their correct behaviour. However, they are inadequate in capturing the intrinsic properties exhibited by these systems. We br…
The testing of Deep Neural Networks (DNNs) has become increasingly important as DNNs are widely adopted by safety critical systems. While many test adequacy criteria have been suggested, automated test input generation for many types of DNNs remains a challenge because the raw input space is too large to randomly sample or to navigate and search for plausible inputs. Consequently, current testing techniques for DNNs depend on small local perturbations to existing inputs, based on the metamorphic testing principle. We propose new ways to search not over the entire image space, but rather over a…
University College London（伦敦大学学院）；Facebook London（Facebook伦敦）；Kyushu University（九州大学）；Nanyang Technological University（南洋理工大学）
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation). The paper also analyses trends concerning datasets, research trends, and research focus, concluding with research challenges and promising research directions in ML testing.
Demographic classification is essential in fairness assessment in recommender systems or in measuring unintended bias in online networks and voting systems. Important fields like education and politics, which often lay a foundation for the future of equality in society, need scrutiny to design policies that can better foster equality in resource distribution constrained by the unbalanced demographic distribution of people in the country. We collect three publicly available datasets to train state-of-the-art classifiers in the domain of gender and caste classification. We train the models in th…
Tel-Aviv University（特拉维夫大学）；The Hebrew University of Jerusalem（希伯来大学）；Bar-Ilan University（巴伊兰大学）；Aarhus University（奥胡斯大学）；IISc Bangalore（印度科学学院班加罗尔分院）
We present a framework that allows to certify the fairness degree of a model based on an interactive and privacy-preserving test. The framework verifies any trained model, regardless of its training process and architecture. Thus, it allows us to evaluate any deep learning model on multiple fairness definitions empirically. We tackle two scenarios, where either the test data is privately available only to the tester or is publicly known in advance, even to the model creator. We investigate the soundness of the proposed approach using theoretical analysis and present statistical guarantees for …
