9 papers
UniAda: Universal Adaptive Multi-objective Adversarial Attack for End-to-End Autonomous Driving Systems
Jingyu Zhang, Jacky Wai Keung, Yan Xiao +3
Adversarial attacks play a pivotal role in testing and improving the reliability of deep learning (DL) systems. Existing literature has demonstrated that subtle perturbations to th…
Empirical Insights of Test Selection Metrics under Multiple Testing Objectives and Distribution Shifts
Jingyu Zhang, Fan Wang, Jacky Keung +3
Deep learning (DL)-based systems can exhibit unexpected behavior when exposed to out-of-distribution (OOD) scenarios, posing serious risks in safety-critical domains such as malwar…
A Comprehensive Study of Bugs in Modern Distributed Deep Learning Systems
Xiaoxue Ma, Wanwei Zhan, Jiale Chen +3
In today's data-driven era, deep learning is vital for processing massive datasets, yet single-device training is constrained by computational and memory limits. Distributed deep l…
PerProb: Indirectly Evaluating Memorization in Large Language Models
Yihan Liao, Jacky Keung, Xiaoxue Ma +2
The rapid advancement of Large Language Models (LLMs) has been driven by extensive datasets that may contain sensitive information, raising serious privacy concerns. One notable th…
Advancing Autonomous Driving System Testing: Demands, Challenges, and Future Directions
Yihan Liao, Jingyu Zhang, Jacky Keung +2
Autonomous driving systems (ADSs) promise improved transportation efficiency and safety, yet ensuring their reliability in complex real-world environments remains a critical challe…
Exposing and Defending Membership Leakage in Vulnerability Prediction Models
Yihan Liao, Jacky Keung, Xiaoxue Ma +2
Neural models for vulnerability prediction (VP) have achieved impressive performance by learning from large-scale code repositories. However, their susceptibility to Membership Inf…