An Empirical Study on Common Defects in Modern Web Browsers Using Knowledge Embedding in GPT-4o

2025-04-29

AI Summary

Prior work lacks a systematic, cross-browser empirical comparison of defect distribution patterns between modern browsers—specifically Chromium and Firefox. Method: We propose the first cross-browser defect comparative analysis framework, integrating GPT-4o knowledge embedding with traditional TF-IDF and K-Means clustering to establish an LLM-driven, interpretable defect classification paradigm. Contribution/Results: Our analysis reveals that Firefox exhibits significantly higher defect density than Chromium, with pronounced heterogeneity in component-level defect propensity. The LLM-based approach achieves superior classification accuracy and semantic interpretability compared to conventional NLP methods. This study bridges a critical gap in cross-platform browser defect pattern analysis, providing both empirical evidence and methodological innovation to enhance browser resilience, optimize test resource allocation, and inform proactive defect prevention strategies.

Technology Category

• Data Mining & Knowledge Management: Knowledge Acquisition from the Web
• Search and Optimization: Distributed Search
• Application Domains: Mobility, Driving & Flight

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Technology is advancing at an unprecedented pace. With the advent of cutting-edge technologies, keeping up with rapid changes are becoming increasingly challenging. In addition to that, increasing dependencies on the cloud technologies have imposed enormous pressure on modern web browsers leading to adapting new technologies faster and making them more susceptible to defects/bugs. Although, many studies have explored browser bugs, a comparative study among the modern browsers generalizing the bug categories and their nature was still lacking. To fill this gap, we undertook an empirical investigation aimed at gaining insights into the prevalent bugs in Google Chromium and Mozilla Firefox as the representatives of modern web browsers. We used GPT-4.o to identify the defect (bugs) categories and analyze the clusters of the most commonly appeared bugs in the two prominent web browsers. Additionally, we compared our LLM based bug categorization with the traditional NLP based approach using TF-IDF and K-Means clustering. We found that although Google Chromium and Firefox have evolved together since almost around the same time (2006-2008), Firefox suffers from high number of bugs having extremely high defect-prone components compared to Chromium. This exploratory study offers valuable insights on the browser bugs and defect-prone components to the developers, enabling them to craft web browsers and web-applications with enhanced resilience and reduced errors.

Problem

• Identifying common defect categories in modern web browsers using GPT-4o
• Comparing bug patterns between Google Chromium and Mozilla Firefox
• Evaluating LLM-based bug categorization versus traditional NLP approaches

Innovation

• Using GPT-4o for bug categorization
• Comparing LLM with traditional NLP methods
• Analyzing defect-prone components in browsers