51²è¹Ý

Abstract: Robust Machine Learning (ML) is arguably the most important technical challenge of current times, to address growing concerns about misuse of AI, violations of data privacy and stealing of trained models. The problem is only exacerbated by lack of explainability for Machine Learning decisions juxtaposed with the tremendous rate of adoption of AI across all industries. In this talk, I will narrate a few research threads pursued in our group. First, I will present a theoretical understanding of adversarial attacks and countermeasures inspired by the same. Second, a case study with the intelligent perception module of a (semi-) autonomous vehicle will be discussed. In that, we will see how various techniques for enhancing robustness of an ML accelerator can be stepwise integrated. The last part of the talk will highlight new directions in ML, such as peer-to-peer federated learning, and how data privacy is impacted in such scenarios.

About the Speaker: Anupam Chattopadhyay received his B.E. degree from Jadavpur University, India, MSc. from ALaRI, Switzerland and PhD from RWTH Aachen in 2000, 2002 and 2008 respectively. From 2008 to 2009, he worked as a Member of Consulting Staff in CoWare R&D, Noida, India. From 2010 to 2014, he led the MPSoC Architectures Research Group in RWTH Aachen, Germany as a Junior Professor. In September, 2014, Anupam was appointed as an Assistant Professor in College of Computing & Data Science, NTU, where he got promoted to Associate Professor with Tenure from August, 2019. In the past, he held visiting positions at Politecnico di Torino, Italy; EPFL, Switzerland; Technion, Israel and Indian Statistical Institute, Kolkata.

Anupam currently heads a team of 20+ researchers, overseeing projects in the area of computer architectures, security, design automation and emerging technologies. His research advances has been reported in more than 100 conference/journal papers (ACM/IEEE/Springer), multiple research monographs and edited books (CRC, Springer) and open-access forums. Together with his doctoral students, Anupam proposed novel research directions like, domain-specific high-level synthesis for cryptography, high-level reliability estimation flows for embedded processors, generalisation of classic linear algebra kernels and multi-layered coarse-grained reconfigurable architecture. Anupam’s research in the area of emerging technologies has been covered by major news outlets across the world, including Asian Scientist, Straits Times and The Economist.

Look forward to your active participation.