Abstract
Based on the tremendous success of pre-trained language models (PrLMs) for source code comprehension tasks, current literature studies either ways to further improve the performance (generalization) of PrLMs, or their robustness against adversarial attacks. However, they have to compromise on the trade-off between the two aspects and none of them consider improving both sides in an effective and practical way. To fill this gap, we propose Semantic-Preserving Adversarial Code Embeddings (SPACE) to find the worst-case semantic-preserving attacks while forcing the model to predict the correct labels under these worst cases. Experiments and analysis demonstrate that SPACE can stay robust against state-of-the-art attacks while boosting the performance of PrLMs for code.- Anthology ID:
- 2022.coling-1.267
- Volume:
- Proceedings of the 29th International Conference on Computational Linguistics
- Month:
- October
- Year:
- 2022
- Address:
- Gyeongju, Republic of Korea
- Editors:
- Nicoletta Calzolari, Chu-Ren Huang, Hansaem Kim, James Pustejovsky, Leo Wanner, Key-Sun Choi, Pum-Mo Ryu, Hsin-Hsi Chen, Lucia Donatelli, Heng Ji, Sadao Kurohashi, Patrizia Paggio, Nianwen Xue, Seokhwan Kim, Younggyun Hahm, Zhong He, Tony Kyungil Lee, Enrico Santus, Francis Bond, Seung-Hoon Na
- Venue:
- COLING
- SIG:
- Publisher:
- International Committee on Computational Linguistics
- Note:
- Pages:
- 3017–3028
- Language:
- URL:
- https://aclanthology.org/2022.coling-1.267
- DOI:
- Cite (ACL):
- Yiyang Li, Hongqiu Wu, and Hai Zhao. 2022. Semantic-Preserving Adversarial Code Comprehension. In Proceedings of the 29th International Conference on Computational Linguistics, pages 3017–3028, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
- Cite (Informal):
- Semantic-Preserving Adversarial Code Comprehension (Li et al., COLING 2022)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2022.coling-1.267.pdf
- Code
- ericlee8/space
- Data
- CodeQA, CodeSearchNet