ABSTRACT
Any given AI system cannot be accepted unless its trustworthiness is proven. An important characteristic of a trustworthy AI system is the absence of algorithmic bias. 'Individual discrimination' exists when a given individual different from another only in 'protected attributes' (e.g., age, gender, race, etc.) receives a different decision outcome from a given machine learning (ML) model as compared to the other individual. The current work addresses the problem of detecting the presence of individual discrimination in given ML models. Detection of individual discrimination is test-intensive in a black-box setting, which is not feasible for non-trivial systems. We propose a methodology for auto-generation of test inputs, for the task of detecting individual discrimination. Our approach combines two well-established techniques - symbolic execution and local explainability for effective test case generation. We empirically show that our approach to generate test cases is very effective as compared to the best-known benchmark systems that we examine.
- Julius Adebayo and Lalana Kagal. 2016. Iterative Orthogonal Feature Projection for Diagnosing Bias in Black-Box Models. arXiv: arXiv:1611.04967Google Scholar
- Cristian Cadar, Vijay Ganesh, Peter M. Pawlowski, David L. Dill, and Dawson R. Engler. 2006. EXE: Automatically Generating Inputs of Death. In Proceedings of the 13th ACM Conference on Computer and Communications Security (CCS ’06). ACM, New York, NY, USA, 322–335. Google ScholarDigital Library
- Mark William Craven. 1996. Extracting Comprehensible Models from Trained Neural Networks. Ph.D. Dissertation. AAI9700774.Google Scholar
- Leonardo de Moura and Nikolaj Bjørner. 2008. Z3: An Efficient SMT Solver. In Tools and Algorithms for the Construction and Analysis of Systems, C. R. Ramakrishnan and Jakob Rehof (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 337–340. Google ScholarDigital Library
- Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, and Richard Zemel. 2012. Fairness Through Awareness. In Proceedings of the 3rd Innovations in Theoretical Computer Science Conference (ITCS ’12). ACM, New York, NY, USA, 214–226. Google ScholarDigital Library
- Michael Feldman, Sorelle A Friedler, John Moeller, Carlos Scheidegger, and Suresh Venkatasubramanian. 2015. Certifying and removing disparate impact. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 259–268. Google ScholarDigital Library
- Sainyam Galhotra, Yuriy Brun, and Alexandra Meliou. 2017. Fairness Testing: Testing Software for Discrimination. In Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering (ESEC/FSE 2017). ACM, New York, NY, USA, 498–510. Google ScholarDigital Library
- Patrice Godefroid. 2007. Compositional Dynamic Test Generation. In Proceedings of the 34th Annual ACM SIGPLAN-SIGACT Symposium on Principles of Programming Languages (POPL ’07). ACM, New York, NY, USA, 47–54. Google ScholarDigital Library
- Patrice Godefroid, Nils Klarlund, and Koushik Sen. 2005. DART: Directed Automated Random Testing. In Proceedings of the 2005 ACM SIGPLAN Conference on Programming Language Design and Implementation (PLDI ’05). ACM, New York, NY, USA, 213–223. Google ScholarDigital Library
- Divya Gopinath, Kaiyuan Wang, Mengshi Zhang, Corina S. Pasareanu, and Sarfraz Khurshid. 2018.Google Scholar
- Symbolic Execution for Deep Neural Networks. arXiv: arXiv:1807.10439Google Scholar
- Pang Wei Koh and Percy Liang. 2017. Understanding Black-box Predictions via Influence Functions. In Proceedings of the 34th International Conference on Machine Learning (Proceedings of Machine Learning Research), Doina Precup and Yee Whye Teh (Eds.), Vol. 70. PMLR, International Convention Centre, Sydney, Australia, 1885–1894. http://proceedings.mlr.press/v70/koh17a.html Google ScholarDigital Library
- Matt Kusner, Joshua Loftus, Chris Russell, and Ricardo Silva. 2017. Counterfactual Fairness. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS’17). Curran Associates Inc., USA, 4069–4079. http: //dl.acm.org/citation.cfm?id=3294996.3295162 Google ScholarDigital Library
- Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, and Yadong Wang. 2018. DeepGauge: multi-granularity testing criteria for deep learning systems. In Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, ASE 2018, Montpellier, France, September 3-7, 2018. 120–131. 3238147.3238202 Google ScholarDigital Library
- Kexin Pei, Yinzhi Cao, Junfeng Yang, and Suman Jana. 2017. DeepXplore: Automated Whitebox Testing of Deep Learning Systems. In Proceedings of the 26th Symposium on Operating Systems Principles (SOSP ’17). ACM, New York, NY, USA, 1–18. Google ScholarDigital Library
- Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2016. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, 1135–1144. Google ScholarDigital Library
- R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra. 2017. Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. In 2017 IEEE International Conference on Computer Vision (ICCV). 618–626.Google Scholar
- Koushik Sen, Darko Marinov, and Gul Agha. 2005. CUTE: A Concolic Unit Testing Engine for C. In Proceedings of the 10th European Software Engineering Conference Held Jointly with 13th ACM SIGSOFT International Symposium on Foundations of Software Engineering (ESEC/FSE-13). ACM, New York, NY, USA, 263–272. Google ScholarCross Ref
- Youcheng Sun, Xiaowei Huang, and Daniel Kroening. 2018. Testing Deep Neural Networks. arXiv: arXiv:1803.04792Google Scholar
- Youcheng Sun, Min Wu, Wenjie Ruan, Xiaowei Huang, Marta Kwiatkowska, and Daniel Kroening. 2018.Google Scholar
- Concolic Testing for Deep Neural Networks. arXiv: arXiv:1805.00089Google Scholar
- Christian Szegedy, Wojciech Zaremba, Ilya Sutskever, Joan Bruna, Dumitru Erhan, Ian J. Goodfellow, and Rob Fergus. 2013. Intriguing properties of neural networks. CoRR abs/1312.6199 (2013). arXiv: 1312.6199 http://arxiv.org/abs/1312.6199Google Scholar
- Yuchi Tian, Kexin Pei, Suman Jana, and Baishakhi Ray. 2018. DeepTest: Automated Testing of Deep-neural-network-driven Autonomous Cars. In Proceedings of the 40th International Conference on Software Engineering (ICSE ’18). ACM, New York, NY, USA, 303–314. Google ScholarDigital Library
- F. TramÃĺr, V. Atlidakis, R. Geambasu, D. Hsu, J. Hubaux, M. Humbert, A. Juels, and H. Lin. 2017. FairTest: Discovering Unwarranted Associations in Data-Driven Applications. In 2017 IEEE European Symposium on Security and Privacy (EuroS P). 401–416.Google Scholar
- Sakshi Udeshi, Pryanshu Arora, and Sudipta Chattopadhyay. 2018. Automated Directed Fairness Testing. Automated Directed Fairness Testing. In Proceedings of the 2018 33rd ACM/IEEE International Conference on Automated Software Engineering (ASE 18), September 3-7, 2018, Montpellier, France. (2018). Google ScholarDigital Library
- arXiv: arXiv:1807.00468Google Scholar
Index Terms
- Black box fairness testing of machine learning models
Recommendations
Latent Imitator: Generating Natural Individual Discriminatory Instances for Black-Box Fairness Testing
ISSTA 2023: Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and AnalysisMachine learning (ML) systems have achieved remarkable performance across a wide area of applications. However, they frequently exhibit unfair behaviors in sensitive application domains (e.g., employment and loan), raising severe fairness concerns. To ...
Fairness testing: testing software for discrimination
ESEC/FSE 2017: Proceedings of the 2017 11th Joint Meeting on Foundations of Software EngineeringThis 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 ...
Achieving both model and code coverage with automated gray-box testing
A-MOST '07: Proceedings of the 3rd international workshop on Advances in model-based testingWe have devised a novel technique to automatically generate test cases for a software system, combining black-box model-based testing with white-box parameterized unit testing. The former provides general guidance for the structure of the tests in the ...
Comments