Effectiveness of Transformer-based Language Models in Detecting Advanced Persistent Threats from System Provenance Graphs (2022 - Current)

Undergraduate thesis project under Dr. Anindya Iqbal and Dr. Shahrear Iqbal(Research Officer, National Research Council (NRC) Canada). In this work, I co-implemented a framework which includes a robust process of creating a provenance graph from raw log data from the DARPA OPTC and DARPA TC E3 datasets, subsequently generating event sequences from that graph and finally transforming the data into a suitable format for transformer-based language models such as BERT, RoBERTa, GPT. My personal contributions were building the postgres database from the raw log datasets, designing SQL queries to generate the provenance graph, co-writing the code for preprocessing the graph data to extract traces with relevant attributes, and finally building the experiments with various pre-trained LLMs. We were able to achieve state of the art performance from our framework in detection of APT attacks. Currently, this work is under review for publication.

Advancing Parallelization in Deep Learning Training: A Novel HSIC-Based Approach and Its Comparative Performance Against Traditional Federated Models (2023 - Current)

Working with Dr. Praneeth Vepakomma (MIT Camera Culture Group) as part of the Fatima Fellowship Research Program, on a distributed machine learning project. We developed a method for parallelizing the forward propagation in neural network training, utlizing the HSIC objective function to eliminate the need for backpropagation, all while maintaining the same level of accuracy. We also discovered that, in some instances, employing slightly outdated local updates can signifcantly reduce communicaton costs without compromising accuracy. We are presently in the phase of manuscript review of this work, as we prepare it for publication.

Development of Flood Forecasting System for Bangladesh-India Using Different Machine Learning Techniques (2020)

In this study, I preprocessed datasets of weather parameters and employed the use of five different machine learning algorithms- exponent back propagation neural network (EBPNN), multilayer perceptron (MLP), support vector regression (SVR), DT Regression (DTR), and extreme gradient boosting (XGBoost), which were used to develop total 180 independent models based on a different combination of time lags for input data and lead time in forecast. Models were developed for Someshwari-Kangsa sub-watershed of Bangladesh’s North Central hydrological region with 5772 km² drainage area.

Dengue Forecasting System (2020-2022)

Worked with Dr. ABM Alim Al Islam, Ramisa Alam, Mashiat Mustaq and Tahiea Taz. In this project, we built a time series forecasting model-based dengue forecast system that predicts the number of dengue cases in any given region based on the recent cases in that region and the state of different weather parameters. My contributions in the project was preprocessing the datasets as well as developing the models using MS Azure Services.

Presented the idea and won the 1st Runner Up position in Microsoft Virtual Hackathon 2022.

[Github]