Semantic Robustness of Models of Source Code
Machine Learning
2022-08-23 v2 Machine Learning
Abstract
Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. (1) We define a powerful adversary that can employ sequences of parametric, semantics-preserving program transformations; (2) we show how to perform adversarial training to learn models robust to such adversaries; (3) we conduct an evaluation on different languages and architectures, demonstrating significant quantitative gains in robustness.
Cite
@article{arxiv.2002.03043,
title = {Semantic Robustness of Models of Source Code},
author = {Goutham Ramakrishnan and Jordan Henkel and Zi Wang and Aws Albarghouthi and Somesh Jha and Thomas Reps},
journal= {arXiv preprint arXiv:2002.03043},
year = {2022}
}