AI writes, we analyze: The ChatGPT python code saga

MF Rabbi, AI Champa, MF Zibran… - Proceedings of the 21st …, 2024 - dl.acm.org
In this study, we quantitatively analyze 1,756 AI-written Python code snippets in the DevGPT
dataset and evaluate them for quality and security issues. We systematically distinguish the …

Sbom generation tools under microscope: A focus on the npm ecosystem

MF Rabbi, AI Champa, C Nachuma… - Proceedings of the 39th …, 2024 - dl.acm.org
Generating accurate Software Bill of Materials (SBOM) is challenging due to the complex
dependencies in the diverse components used in software and also the way software is built …

ChatGPT in action: Analyzing its use in software development

AI Champa, MF Rabbi, C Nachuma… - Proceedings of the 21st …, 2024 - dl.acm.org
The emergence of AI tools such as ChatGPT is being used to assist with software
development, but little is known of how developers utilize these tools as well as the …

Curated datasets and feature analysis for phishing email detection with machine learning

AI Champa, MF Rabbi, MF Zibran - 2024 IEEE 3rd International …, 2024 - ieeexplore.ieee.org
Despite continued research, phishing email attacks are on the rise and there is a lack of rich
curated datasets for training and testing email filtering techniques. To address this, we …

Why phishing emails escape detection: A closer look at the failure points

AI Champa, F Rabbi, MF Zibran - 2024 12th International …, 2024 - ieeexplore.ieee.org
This research uncovers why phishing emails often escape machine learning (ML) detection
algorithms. For training and testing ML algorithms in detecting phishing emails, we produce …

Improving Source Code with Assistance from AI—A Pilot Case Study with ChatGPT

S McDaniel, MF Zibran - 2024 7th International Conference on …, 2024 - ieeexplore.ieee.org
ChatGPT queries were used to provide feedback on five C++ programs selected from
various programming assignments for two graduate-level computer science courses–a …

A quantitative analysis of quality and consistency in ai-generated code

A Clark, D Igbokwe, S Ross… - 2024 7th International …, 2024 - ieeexplore.ieee.org
With the recent emergence of generative AI (Artificial intelligence), Large Language Model
(LLM) based tools such as ChatGPT have become popular assistants to humans in diverse …

Causal Models Applied to Studies within the Mining Software Repository Domain

A LEVINSSON, L FRANSSON - 2024 - odr.chalmers.se
Context: Research conducted in the mining software repository domain commonly utilize
observational data, due to software repositories serving as a rich source of such data …