A closer look into transformer-based code intelligence through code transformation: Challenges and opportunities

Y Li, S Qi, C Gao, Y Peng, D Lo, Z Xu… - arxiv preprint arxiv …, 2022 - arxiv.org
Transformer-based models have demonstrated state-of-the-art performance in many
intelligent coding tasks such as code comment generation and code completion. Previous …

Exploring the effectiveness of llms in automated logging generation: An empirical study

Y Li, Y Huo, Z Jiang, R Zhong, P He, Y Su… - arxiv preprint arxiv …, 2023 - arxiv.org
Automated logging statement generation supports developers in documenting critical
software runtime behavior. Given the great success in natural language generation and …

Exploring the effectiveness of llms in automated logging statement generation: An empirical study

Y Li, Y Huo, Z Jiang, R Zhong, P He… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Automated logging statement generation supports developers in documenting critical
software runtime behavior. While substantial recent research has focused on retrieval-based …

Understanding the Robustness of Transformer-Based Code Intelligence via Code Transformation: Challenges and Opportunities

Y Li, S Qi, C Gao, Y Peng, D Lo… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Transformer-based models have demonstrated state-of-the-art performance in various
intelligent coding tasks such as code comment generation and code completion. Previous …

Limits of machine learning for automatic vulnerability detection

N Risse, M Böhme - arxiv preprint arxiv:2306.17193, 2023 - arxiv.org
Recent results of machine learning for automatic vulnerability detection have been very
promising indeed: Given only the source code of a function $ f $, models trained by machine …

An unbiased transformer source code learning with semantic vulnerability graph

NT Islam, GDLT Parra, D Manuel… - 2023 IEEE 8th …, 2023 - ieeexplore.ieee.org
Over the years, open-source software systems have become prey to threat actors. Even
highly-adopted software has been crippled by unforeseeable attacks, leaving millions of …

Enhancing Source Code Security with LLMs: Demystifying The Challenges and Generating Reliable Repairs

NT Islam, J Khoury, A Seong, E Bou-Harb… - arxiv preprint arxiv …, 2024 - arxiv.org
With the recent unprecedented advancements in Artificial Intelligence (AI) computing,
progress in Large Language Models (LLMs) is accelerating rapidly, presenting challenges …

Causative Insights into Open Source Software Security using Large Language Code Embeddings and Semantic Vulnerability Graph

NT Islam, GDLT Parra, D Manual, M Jadliwala… - arxiv preprint arxiv …, 2024 - arxiv.org
Open Source Software (OSS) security and resilience are worldwide phenomena hampering
economic and technological innovation. OSS vulnerabilities can cause unauthorized …

Unintentional Security Flaws in Code: Automated Defense via Root Cause Analysis

NT Islam, M Bethany, D Manuel, M Jadliwala… - arxiv preprint arxiv …, 2024 - arxiv.org
Software security remains a critical concern, particularly as junior developers, often lacking
comprehensive knowledge of security practices, contribute to codebases. While there are …

VulCausal: Robust Vulnerability Detection Using Neural Network Models from a Causal Perspective

H Kuang, J Zhang, F Yang, L Zhang, Z Huang… - … on Knowledge Science …, 2024 - Springer
Deep learning has showcased remarkable performance in source code vulnerability
detection. However, significant challenges persist in terms of generalization and handling …