Security of Language Models for Code: A Systematic Literature Review

Y Chen, W Sun, C Fang, Z Chen, Y Ge, T Han… - arxiv preprint arxiv …, 2024 - arxiv.org
Language models for code (CodeLMs) have emerged as powerful tools for code-related
tasks, outperforming traditional methods and standard machine learning approaches …

Robustness, security, privacy, explainability, efficiency, and usability of large language models for code

Z Yang, Z Sun, TZ Yue, P Devanbu, D Lo - arxiv preprint arxiv:2403.07506, 2024 - arxiv.org
Large language models for code (LLM4Code), which demonstrate strong performance (eg,
high accuracy) in processing source code, have significantly transformed software …

Automated commit intelligence by pre-training

S Liu, Y Li, X **e, W Ma, G Meng, Y Liu - ACM Transactions on Software …, 2024 - dl.acm.org
GitHub commits, which record the code changes with natural language messages for
description, play a critical role in software developers' comprehension of software evolution …

A survey of neural code intelligence: Paradigms, advances and beyond

Q Sun, Z Chen, F Xu, K Cheng, C Ma, Z Yin… - arxiv preprint arxiv …, 2024 - arxiv.org
Neural Code Intelligence--leveraging deep learning to understand, generate, and optimize
code--holds immense potential for transformative impacts on the whole society. Bridging the …

Mutual Learning-Based Framework for Enhancing Robustness of Code Models via Adversarial Training

Y Wang, Y Chen, Y Zhao, Z Gong, J Chen… - Proceedings of the 39th …, 2024 - dl.acm.org
Deep code models (DCMs) have achieved impressive accomplishments and have been
widely applied to various code-related tasks. However, existing studies show that some …

Attribution-guided Adversarial Code Prompt Generation for Code Completion Models

X Li, G Meng, S Liu, L **ang, K Sun, K Chen… - Proceedings of the 39th …, 2024 - dl.acm.org
Large language models have made significant progress in code completion, which may
further remodel future software development. However, these code completion models are …

A Survey on Adversarial Machine Learning for Code Data: Realistic Threats, Countermeasures, and Interpretations

Y Yang, H Fan, C Lin, Q Li, Z Zhao, C Shen… - arxiv preprint arxiv …, 2024 - arxiv.org
Code Language Models (CLMs) have achieved tremendous progress in source code
understanding and generation, leading to a significant increase in research interests …

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

X Du, M Wen, J Zhu, Z **e, B Ji, H Liu, X Shi… - arxiv preprint arxiv …, 2024 - arxiv.org
Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved
promising results over recent years. However, these models struggle to generalize as they …

Towards robust, secure, and privacy-aware large language models of code

Z YANG - 2024 - ink.library.smu.edu.sg
The field of software engineering has witnessed a surge in large language models
specifically tailored to understand and process code, which we call large language models …