About

Greetings! I'm Md Shahidur Rahaman, currently embarking on an exciting journey as a PhD student in Texas A&M University , College Station with a deep-rooted passion for cybersecurity and software security. I recently graduated with a Master's of Science in Computer Science from Baylor University, where I not only advanced my technical skills but also developed a keen interest in the intricate aspects of software and cyber safety.

I am currently under the mentorship of Nitesh Saxena at the SPIES research lab. My present research focus is at the crossroads of Cybersecurity, Software Engineering. I am also interested in an interdisciplinary area that leverages machine learning (ML) techniques to improve cybersecurity measures and apply cybersecurity principles to safeguard ML systems.

Interest

I am currently focused on the dynamic intersection of Cybersecurity, Software Engineering, Software Security, and Machine Learning. My research aims to:

• Cybersecurity: Develop innovative strategies for advanced threat detection and mitigation, enhancing digital system defenses against emerging cyber threats.
• Software Engineering: Explore efficient, reliable software development methodologies, integrating machine learning to improve the software development life cycle.
• Software Security: Investigate secure coding practices, creating frameworks for security testing to build resilient software systems.
• Machine Learning: Apply machine learning algorithms in cybersecurity for threat and anomaly detection, while addressing AI ethical challenges, biases, and privacy concerns.

My goal is to contribute towards a safer, more secure digital environment through the integration of these key disciplines.

Current Projects

• E2EE Authentication with SAS Protocols:

  I am working on improving End-to-End Encryption (E2EE) authentication mechanisms by leveraging Short Authentication String (SAS) protocols in applications like WhatsApp, Telegram, and WeChat. This project focuses on securing device linking processes, which are often vulnerable to various attacks. My approach aims to enhance the verification phase to prevent potential security breaches. While the solution emphasizes preventing QR code-based exploits and other authentication vulnerabilities, further details on the attack models and verification methods provide a deeper understanding of the project.

• Device Fingerprinting and Privacy in AR/VR Environments

  This project explores how machine learning can be used to identify devices through motion sensor data in Augmented Reality (AR) and Virtual Reality (VR) systems. While these fingerprinting techniques offer potential benefits for device authentication, they raise significant privacy concerns, particularly regarding user tracking and identity exposure. Understanding how device characteristics and user interactions contribute to fingerprinting reveals the broader implications of this research.

• Privacy Risks in AI Assistants on E2EE Platforms

  This research examines how AI assistants functioning within E2EE platforms might unintentionally expose sensitive information despite the presence of encryption. The focus is on understanding how data processing and response generation by AI systems could lead to privacy leaks.