Abstract
Neural network models have become the leading solution for a large variety of tasks, such as classification, natural language processing, and others. However, their reliability is heavily plagued by adversarial inputs: inputs generated by adding tiny perturbations to correctly-classified inputs, and for which the neural network produces erroneous results. In this paper, we present a new method called Robustness Measurement and Assessment (RoMA), which measures the robustness of a neural network model against such adversarial inputs. Specifically, RoMA determines the probability that a random input perturbation might cause misclassification. The method allows us to provide formal guarantees regarding the expected frequency of errors that a trained model will encounter after deployment. The type of robustness assessment afforded by RoMA is inspired by state-of-the-art certification practices, and could constitute an important step toward integrating neural networks in safety-critical systems.
Original language | English |
---|---|
Title of host publication | Neural Information Processing - 29th International Conference, ICONIP 2022, Proceedings |
Editors | Mohammad Tanveer, Sonali Agarwal, Seiichi Ozawa, Asif Ekbal, Adam Jatowt |
Publisher | Springer Science and Business Media Deutschland GmbH |
Pages | 92-105 |
Number of pages | 14 |
ISBN (Print) | 9789819916382 |
DOIs | |
State | Published - 2023 |
Event | 29th International Conference on Neural Information Processing, ICONIP 2022 - Virtual, Online Duration: 22 Nov 2022 → 26 Nov 2022 |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Volume | 1791 CCIS |
ISSN (Print) | 1865-0929 |
ISSN (Electronic) | 1865-0937 |
Conference
Conference | 29th International Conference on Neural Information Processing, ICONIP 2022 |
---|---|
City | Virtual, Online |
Period | 22/11/22 → 26/11/22 |
Bibliographical note
Publisher Copyright:© 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
Keywords
- Adversarial examples
- Certification
- Neural networks
- Robustness