Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
9-2020
Abstract
State-of-the-art deep learning (DL) systems are vulnerable to adversarial examples, which hinders their potential adoption in safetyand 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 builds a probabilistic model to compactly characterize the robustness of RNNs through abstraction. Furthermore, we propose an iterative refinement algorithm to derive a precise abstraction, which enables accurate quantification of the robustness measurement. 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 the state-of-the-art techniques.
Discipline
OS and Networks | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering, Virtual Conference, 2020 September 21-25
First Page
423
Last Page
435
ISBN
9781450367684
Identifier
10.1145/3324884.3416564
Publisher
ACM
City or Country
Virtual Conference
Citation
DU, Xiaoning; LI, Yi; XIE, Xiaofei; MA, Lei; LIU, Yang; and ZHAO, Jianjun.
Marble: Model-based robustness analysis of stateful deep learning systems. (2020). Proceedings of the 35th IEEE/ACM International Conference on Automated Software Engineering, Virtual Conference, 2020 September 21-25. 423-435.
Available at: https://ink.library.smu.edu.sg/sis_research/7088
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.