Ernesto Damiani - Università degli Studi di Milano
Securing Artificial Intelligence/Big Data Pipelines
Monday July 16, 2018 - 9.35-10.35
In the era of the Internet of Things, huge volumes of highly dimensional data are made available at an unprecedented velocity. Computations on such data include: (i) quality improvements (interpolation, sparsity reduction) to make them suitable for feeding Machine Learning (ML) models, (ii) ML models training and tuning (iii) ML models’ in-production operation. While much work has been devoted to ML privacy, several open challenges remain related to preserving data confidentiality and integrity when performing the computation of ML models as a- service . We present a technology-independent methodology for addressing CIA properties when running Artificial Intelligence analytics.
Ernesto Damiani is a professor at the Department of Computer Science at Universita’ degli Studi di Milano, where he leads the SEcure Service-oriented Architectures Research (SESAR) Lab. Ernesto is also the Founding Director of the Center for Cyber-Physical Systems at Khalifa University, in the UAE. He received a honorary doctorate from Institut National des Sciences Appliquées de Lyon, France (2017) for his contributions to research and teaching on Big Data analytics. Ernesto is the Principal Investigator of the H2020 TOREADOR project on Big data as a service. His research spans Cyber-security, Big Data and cloud/edge processing, where he has published over 600 peer-reviewed articles and books. He is Distinguished Scientist of ACM and a recipient of the 2017 Stephen Yau Award.