Write a Blog >>
ASE 2020
Mon 21 - Fri 25 September 2020 Melbourne, Australia
Wed 23 Sep 2020 00:20 - 00:40 at Kangaroo - Software Engineering for AI (1) Chair(s): Song Wang

Deep learning (DL) has recently started to be applied in many applications, e.g., autonomous driving, speech recognition, and natural language processing. Yet, many state-of-the-art DL systems are still vulnerable to adversarial examples, which hinders their adoptions in safety- and security-critical scenarios. While some recent progress has been made in analyzing the robustness of feed-forward neural networks, the robustness analysis for stateful DL systems, such as recurrent neural networks (RNNs), still remains largely uncharted. In this paper, we propose MARBLE, a model-based approach for quantitative robustness analysis of real-world RNN-based DL systems. MARBLE first profiles RNNs using training data to collect information on how models behave under controlled perturbations. We then build a probabilistic model to compactly characterize the behavioral robustness of RNNs, through abstraction. Furthermore, we propose a refinement algorithm to iteratively derive a precise abstraction which enables accurate quantification of the robustness measures. We evaluate the effectiveness of MARBLE on both LSTM and GRU models trained separately with three popular natural language datasets. The results demonstrate that (1) our refinement algorithm is more efficient in deriving an accurate abstraction than the random strategy, and (2) MARBLE enables quantitative robustness analysis, in rendering better efficiency, accuracy, and scalability than state-of-the-art techniques.

Wed 23 Sep

Displayed time zone: (UTC) Coordinated Universal Time change

00:00 - 01:00
Software Engineering for AI (1)NIER track / Research Papers at Kangaroo
Chair(s): Song Wang York University, Canada
Multiple-Boundary Clustering and Prioritization to Promote Neural Network Retraining
Research Papers
Weijun Shen Nanjing University, Yanhui Li Department of Computer Science and Technology, Nanjing University, Lin Chen Nanjing University, YuanLei Han Nanjing University, Yuming Zhou Nanjing University, Baowen Xu State Key Laboratory for Novel Software Technology, Nanjing University
MARBLE: Model-Based Robustness Analysis of Stateful Deep Learning Systems
Research Papers
Xiaoning Du Nanyang Technological University, Yi Li Nanyang Technological University, Singapore, Xiaofei Xie Nanyang Technological University, Lei Ma Kyushu University, Yang Liu Nanyang Technological University, Singapore, Jianjun Zhao Kyushu University
Making Fair ML Software using Trustworthy Explanation
NIER track
Joymallya Chakraborty North Carolina State University, USA, Kewen Peng North Carolina State University, Tim Menzies North Carolina State University, USA
Link to publication DOI Pre-print Media Attached