Full Professor, Skoltech
Head of Research Group, AIRI
15th September 2022, 4:00pm - 5:00pm (GST)
The Robustness of Deep Networks: A Geometrical Perspective
When building predictive models, it is important to take into account the geometric structure of the data - how the observations are located in a multidimensional space. Usually, the location of observations is well described by a manifold. It is obvious that its properties affect the accuracy of the corresponding predictive models. By learning the data manifold, we can identify areas on the manifold in which the predictive model is not robust, and thus it becomes possible both to generate effective adversarial attacks on the model and to protect against them. The presentation describes approaches to generating adversarial attacks and to protecting against them by taking into account properties of the data manifold, as well as, in general, how to compare the real data manifold and data generated by a generative model, and thereby, for example, to identify artificially generated (potentially fake) observations.
Evgeny Burnaev obtained his MSc in Applied Physics and Mathematics from the Moscow Institute of Physics and Technology in 2006. After successfully defending his Ph.D. thesis in Foundations of Computer Science at the Institute for Information Transmission Problem RAS in 2008, Evgeny stayed with the Institute as the head of the IITP Data Analysis and Predictive Modeling Lab. Since 2007 Evgeny Burnaev has carried out many successful industrial projects with Airbus, SAFT, IHI, Sahara Force India Formula 1 team, etc. Currently, Evgeny is the head of the Center of Applied AI in Skoltech. Prof. Burnaev’s current research focuses on developing new algorithms in machine learning and deep learning for approximation of physical models, generative modeling, and manifold learning, with applications to computer vision and 3D reconstruction. The results are published in top computer science conferences (ICML, ICLR, NeurIPS, CVPR, ICCV, and ECCV) and journals. In 2017 Evgeny Burnaev was honored with the Moscow Government Prize for Young Scientists in the category "Transmission, Storage, Processing and Protection of Information" for his scientific contribution and for leading the project "The development of methods for predictive analytics for processing industrial, biomedical and financial data." In 2022 he got a Habilitation (Doctor of Science, Russian highest degree) in mathematical modeling and data analysis.