Taught courses on Computer Architecture, Microprocessor, Operating Systems and Discrete Mathematics

Deployed Mathematical models, built machine learning tools and devised financial engineering solutions

Abstract—A framework designed to detect APT attack patterns leveraging the power of self-attention in transformers. We incorporate customized embedding layers to effectively capture the context of event sequences derived from provenance graphs. While acknowledging the computational overhead associated with training transformer networks, our framework surpasses existing LSTM and Language models regarding APT detection performance. We integrated the model parameters and training procedure from the RoBERTa model and conducted extensive experiments on well-known APT datasets (DARPA OpTC and DARPA TC E3). Our framework achieved superior F1 scores of 98\% and 95\% on the two datasets respectively, surpassing the F1 scores of 96\% and 94\% obtained by LSTM models. Our findings suggest that LogShield's performance benefits from larger datasets and demonstrates its potential for generalization across diverse domains.

Status : Under review, [ArXiv Version]

We will be analyzing several 4G LTE COTs devices to detect any noncompliant behavior that deviates from the protocol specification. Active Automata Learning is being used to infer finite state machine from 4G LTE protocol implementation. The deviation will be detected from the learned FSMs and the protocol specifications. This is a collaboration project under the supervision of Professor Md. Shohrab Hossain.

Status : Ongoing

Abstract— Bangla is the seventh most spoken language by a total number of speakers in the world, and yet the development of an automated grammar checker in this language is an understudied problem. Bangla grammatical error detection is a task of detecting sub-strings of a Bangla text that contain grammatical, punctuation, or spelling errors, which is crucial for developing an automated Bangla typing assistant. Our approach involves breaking down the task as a token classification problem and utilizing state-of-the-art transformer-based models. Finally, we combine the output of these models and apply rule-based post-processing to generate a more reliable and comprehensive result. Our system is evaluated on a dataset consisting of over 25,000 texts from various sources. Our best model achieves a Levenshtein distance score of 1.04. Finally, we provide a detailed analysis of different components of our system.

Status : In Preparation for ACL Workshop, [pdf]