NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification

• URL: http://arxiv.org/abs/2112.13214v1
• Date: Sat, 25 Dec 2021 09:19:39 GMT
• Title: NeuronFair: Interpretable White-Box Fairness Testing through Biased Neuron Identification
• Authors: Haibin Zheng, Zhiqing Chen, Tianyu Du, Xuhong Zhang, Yao Cheng, Shouling Ji, Jingyi Wang, Yue Yu, and Jinyin Chen
• Abstract summary: Deep neural networks (DNNs) have demonstrated their outperformance in various domains. It is crucial to conduct fairness testing before DNNs are reliably deployed to sensitive domains. We propose NeuronFair, a new fairness testing framework that differs from previous work in several key aspects.
• Score: 25.211265460381075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage [1.8238848494579714]
  We propose a novel model-agnostic debiasing framework named MAPPING for fair node classification. Our results show that MAPPING can achieve better trade-offs between utility and fairness, and privacy risks of sensitive information leakage.
  arXiv  Detail & Related papers  (2024-01-23T14:59:46Z)
• Harnessing Neuron Stability to Improve DNN Verification [42.65507402735545]
  We present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feed networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) Preliminary results show that VeriStable is competitive and outperforms state-of-the-art verification tools, including $alpha$-$beta$-CROWN and MN-BaB, the first and second performers of the VNN-COMP, respectively.
  arXiv  Detail & Related papers  (2024-01-19T23:48:04Z)
• Certified Defense on the Fairness of Graph Neural Networks [86.14235652889242]
  Graph Neural Networks (GNNs) have emerged as a prominent graph learning model in various graph-based tasks. malicious attackers could easily corrupt the fairness level of their predictions by adding perturbations to the input graph data. We propose a principled framework named ELEGANT to study a novel problem of certifiable defense on the fairness level of GNNs.
  arXiv  Detail & Related papers  (2023-11-05T20:29:40Z)
• FAIRER: Fairness as Decision Rationale Alignment [23.098752318439782]
  Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues. It is unclear how the trained network makes a fair prediction, which limits future fairness improvements. We propose gradient-guided parity alignment, which encourages gradient-weighted consistency of neurons across subgroups.
  arXiv  Detail & Related papers  (2023-06-27T08:37:57Z)
• Fairify: Fairness Verification of Neural Networks [7.673007415383724]
  We propose Fairify, an approach to verify individual fairness property in neural network (NN) models. Our approach adopts input partitioning and then prunes the NN for each partition to provide fairness certification or counterexample. We evaluated Fairify on 25 real-world neural networks collected from four different sources.
  arXiv  Detail & Related papers  (2022-12-08T23:31:06Z)
• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [59.80140875337769]
  Graph Neural Networks (GNNs) have made rapid developments in the recent years. GNNs can leak private information, are vulnerable to adversarial attacks, can inherit and magnify societal bias from training data. This paper gives a comprehensive survey of GNNs in the computational aspects of privacy, robustness, fairness, and explainability.
  arXiv  Detail & Related papers  (2022-04-18T21:41:07Z)
• Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks [55.531896312724555]
  Bayesian Networks (BNNs) are robust and adept at handling adversarial attacks by incorporating randomness. We create our BNN model, called BNN-DenseNet, by fusing Bayesian inference (i.e., variational Bayes) to the DenseNet architecture. An adversarially-trained BNN outperforms its non-Bayesian, adversarially-trained counterpart in most experiments.
  arXiv  Detail & Related papers  (2021-11-16T16:14:44Z)
• S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration [74.5509794733707]
  We present a novel guided learning paradigm from real-valued to distill binary networks on the final prediction distribution. Our proposed method can boost the simple contrastive learning baseline by an absolute gain of 5.515% on BNNs. Our method achieves substantial improvement over the simple contrastive learning baseline, and is even comparable to many mainstream supervised BNN methods.
  arXiv  Detail & Related papers  (2021-02-17T18:59:28Z)
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information [37.90997236795843]
  Graph neural networks (GNNs) have shown great power in modeling graph structured data. GNNs may make predictions biased on protected sensitive attributes, e.g., skin color and gender. We propose FairGNN to eliminate the bias of GNNs whilst maintaining high node classification accuracy.
  arXiv  Detail & Related papers  (2020-09-03T05:17:30Z)
• Boosting Deep Neural Networks with Geometrical Prior Knowledge: A Survey [77.99182201815763]
  Deep Neural Networks (DNNs) achieve state-of-the-art results in many different problem settings. DNNs are often treated as black box systems, which complicates their evaluation and validation. One promising field, inspired by the success of convolutional neural networks (CNNs) in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations.
  arXiv  Detail & Related papers  (2020-06-30T14:56:05Z)
• Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning [61.93730166203915]
  We argue that traditional notions of fairness are not sufficient when the model is vulnerable to adversarial attacks. We show that measuring robustness bias is a challenging task for DNNs and propose two methods to measure this form of bias.
  arXiv  Detail & Related papers  (2020-06-17T22:22:24Z)
• Bayesian x-vector: Bayesian Neural Network based x-vector System for Speaker Verification [71.45033077934723]
  We incorporate Bayesian neural networks (BNNs) into the deep neural network (DNN) x-vector speaker verification system. With the weight uncertainty modeling provided by BNNs, we expect the system could generalize better on the evaluation data. Results show that the system could benefit from BNNs by a relative EER decrease of 2.66% and 2.32% respectively for short- and long-utterance in-domain evaluations.
  arXiv  Detail & Related papers  (2020-04-08T14:35:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.