no code implementations • 25 Mar 2024 • Benjamin Steenhoek, Md Mahbubur Rahman, Monoshi Kumar Roy, Mirza Sanjida Alam, Earl T. Barr, Wei Le
Large Language Models (LLMs) have demonstrated great potential for code generation and other software engineering tasks.
no code implementations • 4 Dec 2023 • Ashwin Kallingal Joshy, Mirza Sanjida Alam, Shaila Sharmin, Qi Li, Wei Le
We demonstrated that using our cleaned data, LineVul, a SOTA line-level vulnerability detection tool, detected 70 more vulnerable lines and 18 more vulnerable functions, and improved Top 10 accuracy from 66% to 73%.
no code implementations • 7 Nov 2023 • Benjamin Steenhoek, Md Mahbubur Rahman, Shaila Sharmin, Wei Le
Due to the different training objectives and the performance of the models, it is interesting to consider whether the models have learned the semantics of code relevant to vulnerability detection, namely bug semantics, and if so, how the alignment to bug semantics relates to model performance.
no code implementations • 12 Oct 2023 • Md Mahbubur Rahman, Ira Ceka, Chengzhi Mao, Saikat Chakraborty, Baishakhi Ray, Wei Le
Our results show that CausalVul consistently improved the model accuracy, robustness and OOD performance for all the state-of-the-art models and datasets we experimented.
no code implementations • 29 Sep 2023 • Eliska Kloberdanz, Wei Le
Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision.
1 code implementation • 15 Dec 2022 • Benjamin Steenhoek, Hongyang Gao, Wei Le
In this paper, we propose to combine such causal-based vulnerability detection algorithms with deep learning, aiming to achieve more efficient and effective vulnerability detection.
no code implementations • 15 Dec 2022 • Benjamin Steenhoek, Md Mahbubur Rahman, Richard Jiles, Wei Le
Deep learning (DL) models of code have recently reported great progress for vulnerability detection.
1 code implementation • 7 Dec 2021 • Mohammad Wardat, Breno Dantas Cruz, Wei Le, Hridesh Rajan
Also, it can provide actionable insights for fix whereas DeepLocalize can only report faults that lead to numerical errors during training.