Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal JURNAL TEKNOLOGI DAN OPEN SOURCE
Agung Prasetya
Universitas Bhinneka PGRI Tulungagung
Computer Science & IT

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Rule-Based SQL Grammar Validator Syahrul Fajar Laqsono; Agung Prasetya; Mohamad Khoirul Ansor
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 9 No. 1 (2026): Jurnal Teknologi dan Open Source, June 2026
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v9i1.5474

Abstract

This study addresses the growing need for reliable data access systems by focusing on the validation of SQL queries generated from natural language using a Text-to-SQL approach. The primary objective of this research is to evaluate the effectiveness of a rule-based SQL grammar validator in detecting syntactic errors and improving the overall quality of queries generated by Large Language Models (LLMs), particularly in the context of Indonesian language input. The research methodology follows a structured process, including literature review, dataset construction, system design, implementation, and performance evaluation. Two datasets were developed: one for validating the grammar checker using both valid and invalid SQL queries, and another for evaluating the Text-to-SQL system. The validator was implemented using a rule-based system with grammar defined in EBNF and executed using forward chaining inference. The results indicate that the system achieves high performance, with an accuracy of 0.909, precision of 0.857, recall of 1.000, and F1-score of 0.923. The validator successfully identifies common structural errors such as missing table references and incomplete JOIN clauses. However, some limitations remain in detecting more complex syntax patterns. Overall, the integration of the grammar checker significantly enhances the reliability of SQL query generation. In conclusion, the proposed system demonstrates strong effectiveness in syntax validation and contributes to improving the robustness of Text-to-SQL systems.
Neural Network-Based Exfiltration Schema Identification Vetrick Aringga Dicktiony Racero; Agung Prasetya; Taufiq Agung Cahyono
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 9 No. 1 (2026): Jurnal Teknologi dan Open Source, June 2026
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v9i1.5475

Abstract

This study uses the BERT architectural technique to identify schema exfiltration in a neural network-based Text-to-SQL system. The growing usage of Large Language Models (LLM) in Text-to-SQL systems, which may provide a danger of database schema leaking through user prompts, provides the context for this study. This research challenge is how to use a deep learning model to reliably and adaptively identify prompt modifications that could carry out exfiltration techniques. The study employed a deep learning strategy with a feedforward neural network as the classifier and the BERT architecture as the primary encoder. There were 20 classes in all, consisting of 19 exfiltration scheme categories and 1 benign class. The dataset was created using a variety of sources, including WikiSQL, DatabaseAnswers, and educational datasets. It was then subjected to tokenisation, labelling, and normalization processes. The model obtains an accuracy of 0.9462, precision of 0.8425, recall of 0.7483, F1-score of 0.7926, and precise match accuracy of 0.7596, according to the data. Additionally, the study demonstrated that the model outperformed implicit suggestions like role switching and prompt injection in identifying explicit prompts. The study concludes that while there are still issues with enhancing detection capabilities for intricate manipulating patterns, the BERT-based approach can provide good performance in identifying schema exfiltration in Text-to-SQL systems.
Co-Authors Mohamad Khoirul Ansor Syahrul Fajar Laqsono Taufiq Agung Cahyono Vetrick Aringga Dicktiony Racero