Real-time Streaming Anomaly Detection in Dynamic Graphs (Online)

The zoom link is available upon registration.
Password: 005584

Talk
MIDAS finds anomalies or malicious edges in time-evolving graphs. MIDAS can be used to detect intrusions, Denial of Service (DoS), and Distributed Denial of Service (DDoS) attacks. It can also be used to detect financial frauds, and fake ratings/profiles in Social Networks like Twitter, Facebook, Amazon. MIDAS requires constant memory to detect these anomalies in real-time so as to minimize the harm caused by them.
Check out the repo here: https://github.com/Stream-AD/MIDAS

About the Speaker
Siddharth Bhatia is a second-year PhD student at the National University of Singapore (NUS). His research is in Streaming Anomaly Detection. At NUS, he is supported by a Presidents Graduate Fellowship. Before joining NUS, Siddharth completed his undergraduate and master’s degrees from BITS Pilani. Siddharth has previously been recognized as a Young Researcher in the ACM Heidelberg Laureate Forum. He will be applying his research at Amazon Web Services (AWS) this summer. For more details, please visit https://www.comp.nus.edu.sg/~sbhatia/