Preventing Undesirable Behaviors of Neural Networks via Evolutionary Constrained Learning

Changwu Huang1; Zeqi Zhang2; Bifei Mao2; Xin Yao1

10.1109/IJCNN55064.2022.9891926

2022

2022 International Joint Conference on Neural Networks (IJCNN)

2161-4393

978-1-6654-9526-4

2022 International Joint Conference on Neural Networks (IJCNN)

1-7

18-23 July 2022

Padua, Italy

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

The extensive use of artificial intelligence (AI) in the real world brings some potential risks due to the undesirable behavior exhibited by AI systems using data-driven machine learning (ML) at their cores. Thus, preventing undesirable behaviors of ML, such as opacity (lack of transparency and explainability), unfairness (bias or discrimination), unsafety and insecurity, privacy disclosure, etc., is an imperative and pressing challenge. This work proposes an evolutionary constrained learning (ECL) framework for constructing ML models that can satisfy behavioral constraints so that the undesirable behaviors can be prevented. To evaluate our framework, we use it to create neural network models that preclude the undesirable behavior (that is, unfairness) on different benchmark datasets. The experimental results demonstrate the effectiveness of our proposed ECL approach for preventing undesirable behaviors of ML.

Regulated Machine Learning Preventing Undersirable Behavior Evolutionary Constrained Learning Fairness Neural Network

First ; Corresponding

English

CPCI-S

Guangdong Provincial Key Laboratory[2020B121201001] ; Program for Guangdong Introducing Innovative and Enterpreneurial Teams[2017ZT07X386] ; Shenzhen Science and Technology Program[KQTD2016112514355531] ; Southern University of Science and Technology[FA2019061021]

Computer Science ; Engineering ; Neurosciences & Neurology

Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic ; Neurosciences

WOS:000867070900058

IEEE

正式出版

1.Department of Computer Science and Engineering, Research Institute of Trustworthy Autonomous Systems (RITAS), Southern University of Science and Technology, Shenzhen, China
2.Trustworthiness Theory Research Center, Huawei Technologies Co., Ltd., Shenzhen, China

Changwu Huang,Zeqi Zhang,Bifei Mao,et al. Preventing Undesirable Behaviors of Neural Networks via Evolutionary Constrained Learning[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:1-7.