University of Maryland - College Park, United States
Early Academic Pursuits:
He began his academic journey at Bangladesh University of Engineering and Technology (BUET), where he pursued a Bachelor's degree in Computer Science and Engineering from March 2016 to February 2021. His exceptional performance is evident through a CGPA of 3.66/4.0 and an advanced GPA of 3.79/4.0. During his time at BUET, he also received 'Merit Stipends' in five out of seven terms and achieved the prestigious 'Dean's Award' in his Junior year for outstanding academic results.
After completing his undergraduate studies, He delved into the field of education, serving as a Lecturer at the Department of Computer Science and Engineering at United International University from July 2021 to July 2022. His commitment to research led him to join the Data Science and Engineering Research Lab at BUET as a Part-Time Research Assistant from March 2021 to July 2022. Shoumik then transitioned to the Maryland Cybersecurity Center, where he worked as a Graduate Research Assistant under the supervision of Dr. Tudor Dumitras from August 2022 to December 2023. This experience laid the groundwork for his current role as a Graduate Research Assistant at the Department of Computer Science at the University of Maryland, starting in January 2024, with Dr. Soheil Feizi as his supervisor.
Contributions and Research Focus:
He has made significant contributions to the fields of Machine Learning and Security, focusing on Adversarial Machine Learning and Computer Security. His research projects demonstrate both theoretical and empirical robustness in areas such as malware detection. Noteworthy projects include "DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness" and "MAlign: Explainable Static Raw-byte Based Malware Family Classification using Sequence Alignment." These projects showcase his innovative approaches to enhancing the accuracy and robustness of malware detection systems.Additionally, his research extends to studying the effectiveness of machine learning models in detecting malware in real-world scenarios, as evidenced by the project titled "Is Machine Learning Sufficient for Malware Detection in the Wild?"
Accolades and Recognition:
His academic excellence has been acknowledged through various scholarships and achievements. He was awarded the prestigious 'Dean's Fellowship' from the University of Maryland and received the 'Innovation Fund' for research from the ICT division of the Bangladesh government. His achievements also include 'Merit Stipends' from BUET and the 'Talent-Pool Scholarship' during his high school years.
Impact and Influence:
As a Teaching Assistant at the University of Maryland for the course "Data 200: Knowledge in Society: Science, Data, and Ethics" in Fall 2023, He has contributed to the education of future generations. His impact extends beyond the classroom, as demonstrated by his involvement in various extracurricular activities, including serving as the General Secretary of the BUET Photographic Society and President of the Notre Dame Nature Study Society.
Legacy and Future Contributions:
His legacy is marked by his dedication to advancing knowledge in machine learning, cybersecurity, and education. His current pursuit of a Ph.D. in Computer Science and Engineering at the University of Maryland reflects his commitment to furthering research in these domains. As he continues to explore innovative solutions to cybersecurity challenges, He is poised to make lasting contributions to academia and the field of computer science. His research, teaching, and leadership roles position him as a promising figure in shaping the future of technology and security.
Adversarial Robustness of Learning-based Static Malware Classifiers
S Saha, W Wang, Y Kaya, S Feizi
MAlign: Explainable static raw-byte based malware family classification using sequence alignment
S Saha, S Afroz, AH Rahman
MALIGN: Adversarially Robust Malware Family Detection using Sequence Alignment
S Saha, S Afroz, A Rahman
Contrastive Self-Supervised Learning Based Approach for Patient Similarity: A Case Study on Atrial Fibrillation Detection from PPG Signal
SK Shanto, S Saha, AH Rahman, MM Masud, ME Ali