Neural Transfer Learning for Repairing Security Vulnerabilities in C Code
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
In this paper, we address the problem of automatic repair of software vulnerabilities with deep learning. The major problem with data-driven vulnerability repair is that the few existing datasets of known confirmed vulnerabilities consist of only a few thousand examples. However, training a deep learning model often requires hundreds of thousands of examples. In this work, we leverage the intuition that the bug fixing task and the vulnerability fixing task are related and that the knowledge learned from bug fixes can be transferred to fixing vulnerabilities. In the machine learning community, this technique is called transfer learning. In this paper, we propose an approach for repairing security vulnerabilities named VRepair which is based on transfer learning. VRepair is first trained on a large bug fix corpus and is then tuned on a vulnerability fix dataset, which is an order of magnitude smaller. In our experiments, we show that a model trained only on a bug fix corpus can already fix some vulnerabilities. Then, we demonstrate that transfer learning improves the ability to repair vulnerable C functions. We also show that the transfer learning model performs better than a model trained with a denoising task and fine-tuned on the vulnerability fixing task. To sum up, this paper shows that transfer learning works well for repairing security vulnerabilities in C compared to learning on a small dataset.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2019) · arXiv · doi:10.48550/arxiv.1910.13461 · Cited by 8,816 · cited 1×
“language noise functions [51]): tokenmasking replaces tokens with a special token <MASK> in the ’buggy’ function; token deletion removes tokens; and token infilling replaces multiple consecutive tokens with a single <MASK> token.”
BackgroundShin, H.-C., Roth, H. R., Gao, M., Lu, L., Xu, Z., Nogues, I., Yao, J., Mollura, D., & Summers, R. M. (2016) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2016.2528162 · Cited by 5,759
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
Wu, Y., Schuster, M., Chen, Z., Le, Q. V., Norouzi, M., Macherey, W., Krikun, M., Cao, Y., Gao, Q., Macherey, K., et al. (2016) · arXiv · doi:10.48550/arxiv.1609.08144 · Cited by 5,319 · cited 1×
“used in automated translation [19], text summarization [20] and other tasks related to natural language.”
MethodSelf-citationA Survey on Deep Transfer Learning
Tan, C., Sun, F., Kong, T., Zhang, W., Yang, C., & Liu, C. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01424-7_27 · Cited by 3,165
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.139 · Cited by 2,824
Revisiting Unreasonable Effectiveness of Data in Deep Learning Era
Sun, C., Shrivastava, A., Singh, S., & Gupta, A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.97 · Cited by 2,484
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361
Prechelt, L. (1998) · Lecture Notes in Computer Science · doi:10.1007/3-540-49430-8_3 · Cited by 1,649
Defects4J: a database of existing faults to enable controlled testing studies for Java programs
Just, R., Jalali, D., & Ernst, M. D. (2014) · Proceedings of the 2014 International Symposium on Software Testing and Analysis · doi:10.1145/2610384.2628055 · Cited by 1,447
Neural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1162 · Cited by 974 · cited 3×
“Importantly, we utilize the TABLE 16 A Sample of Ablation Results Over 8 Hyperparameters ID Description Results 0 VRepair 21.86% 1 Beam width 1 8.96% Beam width 10 17.61% Beam width 50 (VRepair) 21.86% 2 RNN seq2seq 17.14% Transformer seq2seq (VRepair) 21.86% 3 No vulnerable line identifier 10.99% All vulnerable lines…”
MethodInfluentialNeural Machine Translation of Rare Words with Subword Units
Sennrich, R., Haddow, B., & Birch, A. (2015) · arXiv · doi:10.48550/arxiv.1508.07909 · Cited by 950
Unified Pre-training for Program Understanding and Generation
Ahmad, W., Chakraborty, S., Ray, B., & Chang, K.-W. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.211 · Cited by 642
DeepFix: Fixing Common C Language Errors by Deep Learning
Gupta, R., Pal, S., Kanade, A., & Shevade, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10742 · Cited by 426 · cited 3×
“One of the first papers that used seq2seq learning on source code is DeepFix [35], which is about fixing compiler errors.”
BackgroundOn the naturalness of software
Hindle, A., Barr, E. T., Su, Z., Gabel, M., & Devanbu, P. (2012) · 2012 34th International Conference on Software Engineering (ICSE) · doi:10.1109/icse.2012.6227135 · Cited by 425
An Empirical Study on Learning Bug-Fixing Patches in the Wild via Neural Machine Translation
Tufano, M., Watson, C., Bavota, G., Penta, M. D., White, M., & Poshyvanyk, D. (2019) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3340544 · Cited by 370
The adverse effects of code duplication in machine learning models of code
Allamanis, M. (2019) · Proceedings of the 2019 ACM SIGPLAN International Symposium on New Ideas, New Paradigms, and Reflections on Programming and Software · doi:10.1145/3359591.3359735 · Cited by 284
CodeBERT: A Pre-Trained Model for Programming and Natural Languages
Feng, Z., Guo, D., Tang, D., Duan, N., Feng, X., Gong, M., Shou, L., Qin, B., Liu, T., Jiang, D., et al. (2020) · arXiv · doi:10.48550/arxiv.2002.08155 · Cited by 243
Graph-based, Self-Supervised Program Repair from Diagnostic Feedback
Yasunaga, M., & Liang, P. (2020) · arXiv · doi:10.48550/arxiv.2005.10636 · Cited by 81 · cited 1×
“The same phenomenon has been observed in a compiler error fix system, where pre-training lowers the performance of some specific compiler error types [52].”
Background
Cited by
Impact of Code Language Models on Automated Program Repair
Jiang, N., Liu, K., Lutellier, T., & Tan, L. (2023) · 2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE) · doi:10.1109/icse48619.2023.00125 · Cited by 202
Enhanced automated code vulnerability repair using large language models
de-Fitero-Dominguez, D., Garcia-Lopez, E., Garcia-Cabot, A., & Martinez-Herraiz, J.-J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109291 · Cited by 43
“When compared to VulRepair (Fu et al., 2022) and VRepair (Z. Chen et al., 2022), our models, using smaller beam sizes of 1 and 5 in the original dataset, demonstrate a notable contrast in performance.”
MethodResultInfluentialUnveiling ChatGPT’s usage in open source projects: A mining-based study
Tufano, R., Mastropaolo, A., Pepe, F., Dabic, O., Di Penta, M., & Bavota, G. (2024) · Proceedings of the 21st International Conference on Mining Software Repositories · doi:10.1145/3643991.3644918 · Cited by 38
“…context” Over the years, researchers have developed various forms of recommenders, aimed at suggesting relevant code elements for a given task [44, 86, 111], helping to fix bugs [48, 81, 106, 114] and vulnerabilities [54, 68, 70], and even to automatically document software systems [43, 83, 100].”
BackgroundKulsum, U., Zhu, H., Xu, B., & d'Amorim, M. (2024) · Proceedings of the 1st ACM International Conference on AI-Powered Software · doi:10.1145/3664646.3664770 · Cited by 34
PenHeal: A Two-Stage LLM Framework for Automated Pentesting and Optimal Remediation
Huang, J., & Zhu, Q. (2023) · Proceedings of the Workshop on Autonomous Cybersecurity · doi:10.1145/3689933.3690831 · Cited by 25
Metadata
- Authors
- Chen, Z., Kommrusch, S., & Monperrus, M.
- Venue
- IEEE Transactions on Software Engineering
- Published
- 2023-01-01
- Volume
- 49
- Issue
- 1
- Pages
- 147-165
- ISSN
- 0098-5589 (ISSN-L)
- 1939-3520
- 2326-3881
- OpenAlex
- W3156480510
- Cited by
- 160
- References
- 21
- FWCI
- 64.38
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.