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, and generalizability. To overcome the challenges, we propose NeuronFair, a new DNN fairness testing framework that differs from previous work in several key aspects: (1) interpretable - it quantitatively interprets DNNs' fairness violations for the biased decision; (2) effective - it uses the interpretation results to guide the generation of more diverse instances in less time; (3) generic - it can handle both structured and unstructured data. Extensive evaluations across 7 datasets and the corresponding DNNs demonstrate NeuronFair's superior performance. For instance, on structured datasets, it generates much more instances (~x5.84) and saves more time (with an average speedup of 534.56%) compared with the state-of-the-art methods. Besides, the instances of NeuronFair can also be leveraged to improve the fairness of the biased DNNs, which helps build more fair and trustworthy deep learning systems.
翻译:深心神经网络(DNNS)在各个领域表现优异。然而,它引起了社会关注,即DNNS能否产生可靠和公正的决定,特别是在涉及教育、贷款和就业等宝贵资源分配的敏感领域;在将DNNS可靠地部署到这类敏感领域之前进行公平测试至关重要,即尽可能多地发现违反公平的情况;然而,现有的测试方法仍然有以下三个方面的限制:可解释性、性能和可概括性。为了克服挑战,我们提议了NeuronFair,一个新的DNNNN公平测试框架,与以往工作在若干关键方面不同:(1) 可解释性――它从数量上解释DNNS的违反公平情况,以偏向的决定;(2) 有效――它利用解释结果来引导在较少的时间里产生更多不同的情况;(3) 一般性――它可以处理结构化和无结构化的数据。对7个数据集和相应的DNNNFAir的大规模评价显示了优异性业绩。例如,在结构化数据设置方面,它产生与以前的工作不同之处(Yx5.84)更多的实例,并用更透明性地解释性地解释性地解释DNNNFARARA(也可以节省一个平均的学习速度)。