I investigate how digital traces emerge in systems designed to leave none—advancing forensic science for anonymous networks, intelligent devices, and next-generation cyber threats.

Forensic analysis of anonymous search engines, onion-based networks (e.g., Tor), and privacy-oriented browsers to understand what evidence can be collected and how anonymity degrades in practice.

Studying evidence sources and trace patterns in cross-border e-commerce platforms to support investigations into fraud, abuse, and privacy violations.

Evidence acquisition and analysis in IoT and cyber-physical systems, with emphasis on embedded memory, distributed telemetry, and multi-device event reconstruction.

Machine learning and deep learning models for detecting phishing, malicious network traffic, malware, and ransomware, focusing on robustness and interpretability.

Exploring offensive techniques to evaluate network, web application, and system vulnerabilities through controlled penetration testing and red-team style exercises.

Using LLMs, ML, and Generative AI to support evidence triage, artefact correlation, and report generation while keeping investigators in full control of decisions.

• Diminishing error in real-time data for malware and ransomware detection using ML models.
• Forensic analysis of Temu, AliExpress, and Shein e-commerce platforms.
• Deep learning leaf multiple disease detection.
• YOLO-11 live accident object detection from CCTV.
• Comparative analysis of digital forensic tool efficiency.

Works on predicting heart disease, stroke, breast cancer, and chronic kidney disease from clinical and survey datasets, using comparative model evaluation and early detection strategies.

Contributions to transfer learning models for COVID-19 detection from CT scans, deep learning for chest cancer prognosis, and computational characterization of Nipah virus proteins.

Published work on hybrid PV–wind microgrids, energy storage sizing, energy management in RES-powered DC microgrids, and advanced control strategies in power systems.

Investigating digital trace patterns, privacy weaknesses, and potential anti-forensic behavior in major e-commerce platforms.

Designing and evaluating deep learning models to detect and classify multiple plant leaf diseases for agricultural decision support.

Real-time detection of accidents and hazardous events in CCTV streams using YOLO-11, with emphasis on reliability and latency.

Benchmarking tools such as Autopsy, FTK Imager, and CAINE across acquisition reliability, efficiency, and artefact completeness.

Experimental study of how anonymous search engines and onion-based browsers leave traces on client systems and networks.

Designing supervised and deep learning models to detect phishing, malicious URLs, and ransomware activity using network and content features.

Developing lab scenarios using Nmap, Burp Suite, Metasploit, and OWASP methodologies to teach ethical hacking and penetration testing.

Prototyping workflows where LLMs help with log triage, artefact summarization, and structured report drafting.

Automated water tank alarm system using microcontroller, digital rail gate system design, solar-powered vehicle concepts, and automatic traffic signal design.

Hands-on experience with cybersecurity, digital forensics, ethical hacking, penetration testing, data analysis, and cloud environments.