Mahdieh Zabihi

Papers

Total Citations

H-Index

About

Mahdieh Zabihi is a researcher whose work sits at the intersection of cybersecurity, machine learning, and web analytics. Her primary research focus is on the detection and classification of web robots—automated scripts that can either serve beneficial functions or pose security threats. Her most cited paper, "A density based clustering approach for web robot detection" (2014, 18 citations), introduces an innovative method for distinguishing between human users and automated bots. By applying density-based clustering techniques, Zabihi’s work offers a precise solution to the robot detection problem, helping to protect websites from malicious intrusions while improving server performance by prioritizing legitimate human traffic. This contribution is particularly valuable in an era where bot attacks are increasingly sophisticated. Beyond this flagship study, Zabihi’s research explores broader themes in network security and data mining, demonstrating how clustering algorithms can enhance cybersecurity measures. Her work has been cited by peers working on bot detection, anomaly detection, and web security, underscoring its practical relevance. For students and researchers, Zabihi’s research exemplifies how machine learning can be harnessed to solve real-world security challenges, making the web safer and more efficient for all users.