ASE 2023
Mon 11 - Fri 15 September 2023 Kirchberg, Luxembourg
Thu 14 Sep 2023 13:30 - 13:42 at Room C - Testing AI Systems 4

Deep neural networks (DNNs) are susceptible to bugs, just like other types of software systems. A significant uptick in using DNN, and its applications in wide-ranging areas, including safety-critical systems, warrant extensive research on software engineering tools for improving the reliability of DNN-based systems. One such tool that has gained significant attention in the recent years is DNN fault localization. This paper revisits mutation-based fault localization in the context of DNN models and proposes a novel technique, named deepmufl, applicable to a wide range of DNN models. We have implemented deepmufl and have evaluated its effectiveness using 109 bugs obtained from StackOverflow. Our results show that deepmufl detects 53/109 of the bugs by ranking the buggy layer in top-1 position, outperforming state-of-the-art static and dynamic DNN fault localization systems that are also designed to target the class of bugs supported by deepmufl. Moreover, we observed that we can halve the fault localization time for a pre-trained model using mutation selection, yet losing only 7.55% of the bugs localized in top-1 position.

Thu 14 Sep

Displayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change

13:30 - 15:00
Testing AI Systems 4Research Papers / NIER Track at Room C
13:30
12m
Talk
Mutation-based Fault Localization of Deep Neural NetworksACM Distinguished Paper
Research Papers
Ali Ghanbari Iowa State University, Deepak-George Thomas Dept. of Computer Science, Iowa State University, Muhammad Arbab Arshad Dept. of Computer Science, Iowa State University, Hridesh Rajan Iowa State University
Pre-print
13:42
12m
Talk
Fault Localization for Buggy Deep Learning Framework Conversions in Image Recognition
NIER Track
Nikolaos Louloudakis University of Edinburgh, Perry Gibson University of Glasgow, José Cano University of Glasgow, Ajitha Rajan University of Edinburgh
Pre-print File Attached
13:54
12m
Talk
Towards Safe Automated Refactoring of Imperative Deep Learning Programs to Graph Execution
NIER Track
Raffi Khatchadourian City University of New York (CUNY) Hunter College, Tatiana Castro Vélez City University of New York (CUNY) Graduate Center, Mehdi Bagherzadeh Oakland University, Nan Jia City University of New York (CUNY) Graduate Center, Anita Raja City University of New York (CUNY) Hunter College
Pre-print Media Attached
14:06
12m
Talk
AutoConf : Automated Configuration of Unsupervised Learning Systems using Metamorphic Testing and Bayesian Optimization
Research Papers
Lwin Khin Shar Singapore Management University, Arda Goknil SINTEF Digital, Erik Johannes Husom SINTEF Digital, Sagar Sen , Yan Naing Tun Singapore Management University, Kisub Kim Singapore Management University, Singapore
File Attached
14:18
12m
Talk
An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning SystemsRecorded talk
Research Papers
Ahmed Haj Yahmed École Polytechnique de Montréal, Rached Bouchoucha Polytechnique Montréal, Houssem Ben Braiek Polytechnique Montréal, Foutse Khomh Polytechnique Montréal
Pre-print Media Attached
14:30
12m
Talk
A Majority Invariant Approach to Patch Robustness Certification for Deep Learning ModelsRecorded talk
NIER Track
Qilin Zhou City University of Hong Kong, Zhengyuan Wei City University of Hong Kong, Hong Kong, Haipeng Wang City University of Hong Kong, Wing-Kwong Chan City University of Hong Kong, Hong Kong
Pre-print Media Attached