Anand Muralidhar

Papers

Total Citations

H-Index

About

Anand Muralidhar is a researcher at the forefront of computational advertising and machine learning systems, with a sharp focus on combating fraud in digital ecosystems. His most cited work introduces SLIDR (SLIce-Level Detection of Robots), a real-time deep neural network trained with weak supervision to detect robotic traffic in online advertising at scale. This contribution addresses a critical industry challenge: the need for a detection system that is both comprehensive and agile enough to respond to rapidly shifting fraudulent patterns. By leveraging weak supervision, Muralidhar’s approach achieves high precision without the bottleneck of manual labeling, making it practical for real-world deployment. With 3 citations in a short time, his work is gaining traction among practitioners and researchers tackling ad fraud. Muralidhar’s research stands out for its blend of scalability, speed, and accuracy, offering a robust defense against automated abuse in one of the internet’s largest economic sectors. His work is essential reading for anyone interested in the intersection of machine learning, real-time systems, and digital trust.