Detecting complex patterns of events with significant causal and temporal dependencies across multiple data streams is extremely difficult. Training a complicated model would require a large amount of data, which is unrealistic considering that complex events often are rare. For instance, only a tiny fraction of CCTV footage shows violence, and only a minor fraction of activities recorded in computer systems are acts of Advanced Persistent Threats (APTs).

Neuro-symbolic architectures can deliver excellent results, especially when features are linked together through effective probabilistic circuits compiled from human-generated logic. Moreover, uncertainty-awareness is shown to raise the trust human operators can have when using such autonomous architectures.

Indeed, there is no such thing as a certain datum in the real world: everything comes with shades of uncertainty. Traditional uncertainty estimation methodologies in AI aim at quantifying it via point probabilities, which can be more misleading than other approaches such as Bayesian statistics.

Starting from the role that (probabilistic) logics has in supporting human sensemaking (Toniolo et al. 2015; Cerutti and Thimm 2019), in this talk, Dr Federico Cerutti will illustrate how we can encompass efficient and effective uncertainty-aware learning and reasoning in probabilistic circuits (Cerutti et al. 2019; 2021) and neural networks (Sensoy et al. 2020). He will then illustrate two neuro-symbolic architectures for complex event processing (Xing et al. 2020; Roig Vilamala et al. 2020) and discuss their uncertainty-awareness future extensions and potential real-world impact, including in cyber-threat intelligence analysis (Baroni et al. 2021).

This event is hosted by our Distributed Analytics, Information Science (DAIS) group.

Speaker Bio

Dr Federico Cerutti is a Rita Levi-Montalcini Fellow at the University of Brescia and Chair of the University of Brescia branch of the Italian Cybersecurity National Laboratory.

His research is about learning and reasoning with uncertain and sparse data for supporting (cyber-threat) intelligence analysis. Dr Cerutti has co-authored more than 50 peer-reviewed papers, including several journal papers, and co-edited two books. More details can be found on Google Scholar and DBLP.

When: 12-1pm, Thursday 20th January 2021

Where: This event will be held on Zoom. To register, follow this link. Once you have registered, you will be sent the link and passcode to access the call.

Contact: [email protected]