Tutorial 1
Thursday May 19, 11h00 – 12h30
Information Security & Risk Management: trustworthiness and human interaction
Presenters: Nicholas Fair, Stephen Phillips (University of Southampton), Gencer Erdogan, Ragnhild Halvorsrud (SINTEF)
Abstract: For those interested in state-of-the-art approaches to trustworthy cybersecurity risk management that is able to effectively and sufficiently account for the risks that humans introduce into any information system, this tutorial is for you. After establishing that we all understand the same basic concepts around cybersecurity, trustworthiness, system modelling, risk management and socio-technical theory, we will then explore the importance and role of visualised attack paths in providing easily understood risks and supporting humans in choosing appropriate mitigations (thereby ensuring intelligent risk management tools do not become ‘black boxes’ to their users), and how attack paths help pinpoint the most effective risk mitigation strategies. Next, we will investigate human interaction flows and how they can combine with attack paths to empower comprehensive cybersecurity risk assessments and help guide holistic mitigations. In the final third of the tutorial, you will get hands-on with the Security System Modeller tool and Human and Organisation Risk Modelling flow charts to start modelling an information system and identifying and mitigating the cybersecurity risks to it. You will need to bring your laptops to this tutorial.
Tutorial 2
Thursday May 19, 14h00 – 15h30
The Challenge of Collecting and Analyzing Information From Citizens and Social Media in Emergencies: the Crowd4SDG Experience and Tools
Presenters: Barbara Pernici, Carlo Alberto Bono (Politecnico di Milano), Mehmet Oguz Mulayim (IIIA-CSIC), Jose Luis Fernandez-Marquez (University of Geneva)
Abstract: Every year more than 150 million people worldwide are affected by natural disasters. As declared by the United Nations Office for the Coordination of Humanitarian Affairs, “The first 72 hours after a disaster are crucial; response must begin during that time to save lives”. Social media has been demonstrated to be a potential data source to provide actionable data just after a disaster happens, thus allowing emergency responders to better coordinate their activities. In this tutorial, we will see how crowdsourcing assisted by artificial intelligence can make a significant contribution, especially where critical thinking and decision making are needed, in extracting actionable information from unconventional data sources. The experiences with social media analysis, geolocalization, and crowdsourcing obtained in a recently concluded H2020 project E2mC (Evolution of Emergency Copernicus services) and in the on-going H2020 project Crowd4SDG (Citizen Science for Monitoring Climate Impacts and Achieving Climate Resilience) will be illustrated.
Tutorial 3
Thursday May 19, 16h00 – 17h30
Information Science Research with Machine Learning: Best Practices and Pitfalls
Presenter: Andreas Vogelsang (University of Köln)
Abstract: Research on Information Science is increasingly based on the use of techniques from machine learning (ML). ML becomes so prevalent in IS research because of the ever-growing availability of data and the ease of using ML algorithms out of the box based on frameworks and libraries. Although ML algorithms are so approachable, researchers can still make a lot of methodological mistakes that may invalidate a study or, if these flaws are not detected by unaware reviewers, lead to invalid conclusions in published IS research papers. This tutorial aims to:
- Provide an overview of ML techniques and their capabilities for IS research.
- Describe the typical steps of an ML pipeline.
- Make participants aware of best practices and the most common pitfalls when applying ML for IS research.
