ICSE 2024
Fri 12 - Sun 21 April 2024 Lisbon, Portugal
Fri 19 Apr 2024 15:30 - 16:00 at Open Space - Posters 6

This paper addresses how to detect fairness violations in machine learning models systematically with in-distribution testing data. We propose a novel reinforcement learning based exploratory testing approach for individual fairness, namely Mahalanobis Distances Guided Adaptive Boltzmann Fairness Testing (MABFT), which searches for individual discriminatory instances under an adap- tive Boltzmann exploration strategy with the guidance of Mahalanobis distances toward a training data distribution. Thus, through learning a more accurate state-action value approximation, MABFT can explore a much wider valid input space and sharply reduce the number of duplicate instances visited, hence generating more unique tests and identifying more individual discriminatory instances close to the training data distribution. Compared with the state-of-the-art black-box and white-box fairness testing methods, our approach generates on average 79.56% more unique tests and identifies 515.12% more individual discriminatory instances with a performance speed-up of 274.14%. Moreover, the models retrained with the individual discriminatory instances identified by MABFT exhibit on average a 64.93% boost in individual fairness, 41.38% higher than those by the state-of-the-art fairness testing methods.

Fri 19 Apr

Displayed time zone: Lisbon change

15:30 - 16:00
Posters 6Posters at Open Space
15:30
30m
Poster
Causal Graph Fuzzing for Fair ML Sofware Development
Posters
Verya Monjezi University of Texas at El Paso, Ashish Kumar , Gang Tan Pennsylvania State University, Ashutosh Trivedi University of Colorado Boulder, Saeid Tizpaz-Niari University of Texas at El Paso
15:30
30m
Poster
Multi-source Anomaly Detection For Microservice Systems
Posters
Zhengxin Li Inner Mongolia University, Junfeng Zhao Inner Mongolia University, Jia Kang Inner Mongolia University
15:30
30m
Poster
Boosting Individual Fairness through Mahalanobis Distances Guided Boltzmann Exploratory Testing (Extended Abstract)
Posters
Kaixiang Dong School of Intelligent Science and Technology, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China, Peng Wu Institute of Software, Chinese Academy of Sciences, China
15:30
30m
Poster
ICLNet: Stepping Beyond Dates for Robust Issue-Commit Link Recovery
Posters
Abhishek Kumar Indian Institute of Technology Kharagpur, Partha Pratim Das Indian Institute of Technology, Kharagpur, Partha Pratim Chakrabarti Indian Institute of Technology, Kharagpur
15:30
30m
Poster
NomNom: Explanatory Function Names for Program Synthesizers
Posters
Amirmohammad Nazari University of Southern California, Souti Chattopadhyay University of Southern California, Swabha Swayamdipta University of Southern California, Mukund Raghothaman University of Southern California
15:30
30m
Poster
Extracting Relevant Test Inputs from Bug Reports for Automatic Test Case Generation
Posters
Wendkuuni Arzouma Marc Christian OUEDRAOGO University of Luxembourg, Laura Plein University of Luxembourg, Abdoul Kader Kaboré University of Luxembourg, Andrew Habib ABB Corporate Research, Germany, Jacques Klein University of Luxembourg, David Lo Singapore Management University, Tegawendé F. Bissyandé University of Luxembourg
15:30
30m
Poster
F-CodeLLM: A Federated Learning Framework for Adapting Large Language Models to Practical Software Development
Posters
Zeju Cai the School of Software Engineering, Sun Yat-sen University, China, Jianguo Chen the School of Software Engineering, Sun Yat-sen University, China, Wenqing Chen Sun Yat-sen University, Weicheng Wang the School of Software Engineering, Sun Yat-sen University, China, Zibin Zheng Sun Yat-sen University
15:30
30m
Poster
How are Contracts Used in Android Mobile Applications?
Posters
David R. Ferreira Faculty of Engineering, University of Porto, Alexandra Mendes University of Porto and HASLab, INESC TEC, João F. Ferreira INESC-ID and IST, University of Lisbon
15:30
30m
Poster
Creating Fair Software: Identifying and Mitigating Bias in Machine Learning Models through Counterfactual Thinking
Posters
Zhipeng Yin Florida International University, Zichong Wang Florida International University, Wenbin Zhang Florida International University
15:30
30m
Poster
Automated Security Repair for Helm Charts
Posters
Francesco Minna Vrije Universiteit Amsterdam, Agathe Blaise Thales SIX GTS France, Fabio Massacci University of Trento; Vrije Universiteit Amsterdam, Katja Tuma Vrije Universiteit Amsterdam
15:30
30m
Poster
Path Complexity Analysis for Interprocedural Code
Posters
Mira Kaniyur Harvey Mudd College, Ana Cavalcante-Studart Harvey Mudd College, Yihan Yang Harvey Mudd College, Sangeon Park Harvey Mudd College, David Chen Harvey Mudd College, Duy Lam Harvey Mudd College, Lucas Bang Harvey Mudd College
15:30
30m
Poster
NL2Fix: Generating Functionally Correct Code Edits from Bug Descriptions
Posters
Sarah Fakhoury Microsoft Research, Saikat Chakraborty Microsoft Research, Madan Musuvathi Microsoft Research, Shuvendu K. Lahiri Microsoft Research