Pranjal Aggarwal

Hey, thanks for stopping by! 👋

I am a graduate student at the University of Colorado Boulder, advised by Dr. Theodora Chaspari, majoring in Computer Science. As a research student, I am broadly interested in all aspects of machine learning and big data. Specifically, my interest leans towards Natural Language Processing and the integration of structured knowledge with statistical models. Lately, I’ve been intrigued by large language models (LLMs), and I’m currently working on investigating their explainability and reasoning abilities. I’ll be graduating in May 2025 and am actively looking for full-time opportunities in the field of machine learning.

Before my graduate studies, I earned my bachelor’s degree in Computer Science from the Indian Institute of Information Technology (IIIT) Dharwad where I was advised by Dr. Pavan Kumar C. Under the guidance of Dr. Shivakumara Palaiahnakote and Dr. Pavan, I completed my senior year research titled “A New Genetic Algorithm-Based Network for Text Localization in Degraded Social Media Images” which was published in IET Image Processing.

Outside of academia, I enjoy staying active with sports and exploring new destinations through travel.

selected publications

Random Decision Forest Approach for Mitigating SQL Injection Attacks

Pranjal Aggarwal, Akash Kumar, Kshitiz Michael, and 3 more authors

In IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India , 2021

Best Paper Abs DOI Bib

The paper was selected as the student best paper

Structured Query Language (SQL) is extensively used for storing, manipulating and retrieving information in the relational database management system. Using SQL statements, attackers will try to gain unauthorized access to databases and launch attacks to modify/retrieve the stored data, such attacks are called as SQL injection attacks. Such SQL Injection (SQLi) attacks tops the list of web application security risks of all the times. Identifying and mitigating the potential SQL attack statements before their execution can prevent SQLi attacks. Various techniques are proposed in the literature to mitigate SQLi attacks. In this paper, a random decision forest approach is introduced to mitigate SQLi attacks. From the experimental results, we can infer that the proposed approach achieves a precision of 97% and an accuracy of 95%.
@inproceedings{9622689sqli, author = {Aggarwal, Pranjal and Kumar, Akash and Michael, Kshitiz and Nemade, Jagrut and Sharma, Shubham and C, Pavan Kumar}, booktitle = {IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)}, title = {Random Decision Forest Approach for Mitigating SQL Injection Attacks}, pages = {1-5}, doi = {10.1109/CONECCT52877.2021.9622689}, year = {2021}, dimensions = {true}, location = {Bangalore, India}, acceptance = {Accepted}, acceptance_rate = {7\%} }