TCSE logo 
 Sigsoft logo
Sustainability badge
Wed 30 Apr 2025 16:45 - 17:00 at 210 - SE for AI with Security Chair(s): Lina Marsso

Numerous machine learning (ML) models have been developed, including those for software engineering (SE) tasks, under the assumption that training and testing data come from the same distribution. However, train and test distributions often differ, as training datasets rarely encompass the entire distribution, while test distribution tends to shift over time. Hence, when confronted with out-of-distribution (OOD) instances that differ from the training data, a reliable and trustworthy SE ML model must be capable of detecting them to either abstain from making predictions, or potentially forward these OODs to appropriate models handling other categories or tasks.

In this paper, we develop two types of SE-specific OOD detection models, unsupervised and weakly-supervised OOD detection for code. The unsupervised OOD detection approach is trained solely on in-distribution samples while the weakly-supervised approach utilizes a tiny number of OOD samples to further enhance the detection performance in various OOD scenarios. Extensive experimental results demonstrate that our proposed methods significantly outperform the baselines in detecting OOD samples from four different scenarios simultaneously and also positively impact a main code understanding task.

Wed 30 Apr

Displayed time zone: Eastern Time (US & Canada) change

16:00 - 17:30
SE for AI with SecurityResearch Track at 210
Chair(s): Lina Marsso École Polytechnique de Montréal
16:00
15m
Talk
Understanding the Effectiveness of Coverage Criteria for Large Language Models: A Special Angle from Jailbreak AttacksSecuritySE for AIArtifact-Available
Research Track
shide zhou Huazhong University of Science and Technology, Li Tianlin NTU, Kailong Wang Huazhong University of Science and Technology, Yihao Huang NTU, Ling Shi Nanyang Technological University, Yang Liu Nanyang Technological University, Haoyu Wang Huazhong University of Science and Technology
16:15
15m
Talk
Diversity Drives Fairness: Ensemble of Higher Order Mutants for Intersectional Fairness of Machine Learning SoftwareSecuritySE for AI
Research Track
Zhenpeng Chen Nanyang Technological University, Xinyue Li Peking University, Jie M. Zhang King's College London, Federica Sarro University College London, Yang Liu Nanyang Technological University
Pre-print
16:30
15m
Talk
HIFI: Explaining and Mitigating Algorithmic Bias through the Lens of Game-Theoretic InteractionsSecuritySE for AIArtifact-Available
Research Track
Lingfeng Zhang East China Normal University, Zhaohui Wang Software Engineering Institute, East China Normal University, Yueling Zhang East China Normal University, Min Zhang East China Normal University, Jiangtao Wang Software Engineering Institute, East China Normal University
16:45
15m
Talk
Towards More Trustworthy Deep Code Models by Enabling Out-of-Distribution DetectionSecuritySE for AI
Research Track
Yanfu Yan William & Mary, Viet Duong William & Mary, Huajie Shao College of William & Mary, Denys Poshyvanyk William & Mary
17:00
15m
Talk
FairSense: Long-Term Fairness Analysis of ML-Enabled SystemsSecuritySE for AIArtifact-FunctionalArtifact-AvailableArtifact-Reusable
Research Track
Yining She Carnegie Mellon University, Sumon Biswas Carnegie Mellon University, Christian Kästner Carnegie Mellon University, Eunsuk Kang Carnegie Mellon University
:
:
:
: