About

Aniruddha Saha is a PhD candidate in Computer Science at the University of Maryland Baltimore County, with a keen interest in identifying and mitigating adversarial vulnerabilities in deep learning models. His research focuses on backdoor attacks in CNNs, where he has curated attacks and built fast solutions to identify backdoors. He has also investigated how spatial context introduces vulnerabilities in fast object detectors like YOLO and proposed methods to train detectors robust to contextual adversarial patches. Aniruddha has worked as a Machine Learning Research Intern at Bosch Center for AI, an Applied Scientist Intern at Amazon Rekognition, and a Machine Learning Intern at Matroid. Prior to this, he was a Software Engineer at Samsung Research Institute Bangalore, India, where he was part of the DRAM Group of Samsung Semiconductor India Research. Aniruddha's education history includes a Ph.D. in Computer Science from the University of Maryland, a Bachelor of Engineering from Jadavpur University, and a High School degree from Hem Sheela Model School, Durgapur. He also spent some time in St. Michael's School, Durgapur, and Don Bosco School, Siliguri. Apart from his academic and professional pursuits, Aniruddha enjoys photography, writing, and playing chess. He is a big football fan and supports Manchester United FC. Overall, Aniruddha Saha is a highly skilled and motivated researcher with a strong background in machine learning and artificial intelligence. His experience in both academia and industry has given him a unique perspective on identifying and mitigating adversarial vulnerabilities in deep learning models.