Learning models for phishing detection


Phishing is one of the most common cyber attacks today. In a phishing attack, an attacker deploys a malicious website that resembles a legitimate website, and sends a link of the phishing website to potential victims, with the goal of stealing sensitive information such as user credentials (username and password), bank account details, and even entire identities. As the phishing ecosystem continues to grow in sophistication, the research community has been exploring advanced algorithms---specifically machine learning (and deep learning) models---that leverage and learn from large-scale data to detect and effectively counter phishing attacks. In this talk, we discuss different machine learning (ML) based phishing detection solutions, how they differ and complement each other, as well as the challenges in building and sustaining ML-based detection solutions in practice.

The Speaker

Dr. Dinil Mon Divakaran heads Trustwave Research, the global cyber security R&D unit of Trustwave (a Singtel company). He is a senior research lead, working in the cross domains of cyber security and AI (Applied Statistics, Machine/Deep Learning, NLP, Data Mining, etc.). He is also an Adjunct Assistant Professor of School of Computing in NUS (National University of Singapore). Prior to this, he led network security research at the A*STAR Institute for Infocomm Research(I²R). His research experience cuts across both industry and academia. He previously held faculty position at the Indian Institute of Technology (IIT)Mandi. He carried out his doctoral studies at the INRIA lab in ENS Lyon in France, in collaboration with Bell Labs.