.png){kind=icon}
.png){kind=icon}
Return
CoCoFuzzing: Testing Neural Code Models With Coverage-Guided Fuzzing
.png){kind=icon}
PRE
AI
DOI：10.1109/TR.2022.3208239.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Deep learning (DL)-based code processing models have demonstrated good performance for tasks such as method name prediction, program summarization, and comment generation. However, despite the tremendous advancements, DL models are frequently susceptible to adversarial attacks, which pose a significant threat to the robustness and generalizability of these models by causing them to misclassify unexpected inputs. To address the issue above, numerous DL testing approaches have been proposed; however, these approaches primarily target testing DL applications in the domains of image, audio, and text analysis, etc., and cannot be directly applied to neural models for code due to the unique properties of programs. In this article, we propose a coverage-based fuzzing framework, CoCoFuzzing, for testing DL-based code processing models. In particular, we first propose 10 mutation operators to automatically generate validly and semantically preserving source code examples as tests, followed by a neuron coverage (NC)-based approach for guiding the generation of tests. The performance of CoCoFuzzing is evaluated using three state-of-the-art neural code models, i.e., NeuralCodeSum, CODE2SEQ, and CODE2VEC. Our experiment results indicate that CoCoFuzzing can generate validly and semantically preserving source code examples for testing the robustness and generalizability of these models and enhancing NC. Furthermore, these tests can be used for adversarial retraining to improve the performance of neural code models.
Keywords:
Codes
Testing
Fuzzing
Neurons
Software
Biological neural networks
Task analysis
Code model
deep learning (DL)
fuzzy logic
language model
robustness
Journal
IF:
5.7
Papers:
2.7K
Citations:
8.5K
Organization
View more organizations