Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
5-2025
Abstract
Deep Learning (DL) has achieved significant success in socially critical decision-making applications but often exhibits unfair behaviors, raising social concerns. Among these unfair behaviors, individual discrimination-examining inequalities between instance pairs with identical profiles differing only in sensitive attributes such as gender, race, and age-is extremely socially impactful. Existing methods have made significant and commendable efforts in testing individual discrimination before deployment. However, their efficiency and effectiveness remain limited, particularly when evaluating relatively fairer models. It remains unclear which phase of the existing testing framework (global or local) is the primary bottleneck limiting performance. Facing the above issues, we first identify that enhancing the global phase consistently improves overall testing effectiveness compared to enhancing the local phase. This motivates us to propose Genetic-Random Fairness Testing (GRFT), an effective and efficient method. In the global phase, we use a genetic algorithm to guide the search for more global discriminatory instances. In the local phase, we apply a light random search to explore the neighbors of these instances, avoiding time-consuming computations. Additionally, based on the fitness score, we also propose a straightforward yet effective repair approach. For a thorough evaluation, we conduct extensive experiments involving 6 testing methods, 5 datasets, 261 models (including 5 naively trained, 64 repaired, and 192 quantized for on-device deployment), and sixteen combinations of sensitive attributes, showing the superior performance of GRFT and our repair method.
Keywords
Individual Discrimination, Fairness, DNNs
Discipline
Programming Languages and Compilers | Software Engineering
Research Areas
Intelligent Systems and Optimization
Areas of Excellence
Digital transformation
Publication
Proceedings of the ICSE 2025 47th International Conference on Software Engineering, Ontario, Canada, April 27 - May 3
First Page
1908
Last Page
1920
Identifier
10.1109/ICSE55347.2025.00235
Publisher
IEEE
City or Country
Los Alamitos, CA
Citation
QUAN, Lili; LI, Tianlin; XIE, Xiaofei; CHEN, Zhenpeng; CHEN, Sen; JIANG, Lingxiao; and LI, Xiaohong.
Dissecting global search: A simple yet effective method to boost individual discrimination testing and repair. (2025). Proceedings of the ICSE 2025 47th International Conference on Software Engineering, Ontario, Canada, April 27 - May 3. 1908-1920.
Available at: https://ink.library.smu.edu.sg/sis_research/10328
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/ICSE55347.2025.00235