Speaker 1: Dr. Deborah Sulem, Postdoctoral Researcher, Barcelona School of Economics- Universitat Pompeu Febra

Title:  Scalable and adaptive variational Bayes methods for Hawkes processes

Abstract: Hawkes processes are applied to model dependence and interaction phenomena in multivariate event data sets, such as neuronal spike trains, social interactions, and financial transactions. In the nonparametric setting, learning the temporal dependence structure of Hawkes processes is generally a computationally expensive task, all the more with Bayesian estimation methods. Recently, efficient mean-field variational algorithms have been proposed. In this work, we unify existing variational Bayes approaches under a general nonparametric inference framework, and analyse the asymptotic properties of these methods under easily verifiable conditions. Then, we propose a novel sparsity-inducing procedure, and derive an adaptive mean-field variational algorithm for the popular sigmoid Hawkes processes. Our algorithm is parallelisable and therefore computationally efficient in high-dimensional setting. 

Speaker 2: Ms. Solaleh Mohammadi, PhD Student, Sharif University of Techonology

Title: Semantic backdoor attacks

Abstract: In this presentation, we explore a cutting-edge technique that leverages diffusion models to craft natural triggers for backdoor attacks in machine learning systems. Diffusion models have garnered attention for their remarkable data generation capabilities. However, we reveal their innovative application as tools for adversaries aiming to introduce subtle triggers into deep learning models. These natural triggers can activate specific behaviors, potentially compromising model integrity and security.