Evaluating and Enhancing the Robustness of Code Pre-trained Models through Structure-Aware Adversarial Samples Generation

Nuo Chen, Qiushi Sun, Jianing Wang, Ming Gao, Xiaoli Li, Xiang Li

Submission Type: Regular Long Paper

Submission Track: NLP Applications

Keywords: Neural Code Intelligence, Pre-trained Language Models, Adversarial Attack

TL;DR: We leverage the code structure to generate adversarial examples to attack code pre-trained models, and then enhance model robustness with adversarial training strategies by exploiting the structural information.

Abstract:

Code pre-trained models (CodePTMs) have significantly advanced the field of neural code intelligence. Despite their capabilities,
these models are susceptible to adversarial attacks that subtly modify the model inputs, resulting in incorrect outputs or predictions. Previous methods of robustness evaluation for CodePTMs primarily stem from a textual perspective, without explicitly taking into account the structure of the code. Furthermore, prior studies fail to encompass a broad enough spectrum of tasks and models. In this paper, we propose a set of novel robustness evaluation methods based on the intrinsic structure of the code. Specifically, we first launch adversarial attacks on crucial identifier tokens and sub-tree structures to explore the impact of imperceptible perturbation. Then, we perform global restructuring of the code using different traversal methods for abstract syntax trees, aiming to explore the model's sensitivity to input samples with equivalent information. Moreover, for each scenario, we employ adversarial training methods to explore the possibility of restoring the performance of perturbed models. For both code understanding and generation, our proposed method has demonstrated its effectiveness across a wide range of models and tasks, thereby allowing us to make one step forward in our understanding of the inner mechanisms of CodePTMs.

Submission Number: 714