In this talk, I will discuss our recent efforts to study user activity on popular OSNs and other websites, as well as the continuous user tracking from such platforms, potentially leading to severe implications on their privacy. In particular, first, I will cover our extensive studies to detect and characterize inappropriate content and behavior on social media such as Twitter and YouTube, including manifestation and propagation of aggressive, abusive or bullying behavior, fraudulent crowdfunding campaigns and fake news. Then, I will discuss in depth how tracking of users from online entities (first and third-parties), initiated by various advertising protocols, leads to increased violations in the privacy of said users, with typical offenders being popular OSNs and other online ad-platforms. I will conclude with novel alternatives from such companies on building useful machine learning models on the online user side, without violating their users' privacy.
Nicolas Kourtellis is a Principal Research Scientist at Telefonica R&D, Barcelona, Spain. He holds a PhD in Computer Science & Engineering from the University of South Florida, USA (2012). Before Telefonica R&D, he did research at Yahoo Labs, USA, on online user privacy and behavior modeling, Internet measurements and distributed systems, with 70+ published peer-reviewed papers and 6 filed patents. Lately, he focuses on CyberPrivacy (Privacy-preserving Machine Learning (ML) and Federated Learning on the edge, user online privacy and PII leaks), etc.) and CyberSafety (modeling and detecting abusive, inappropriate or fraudulent content on social media using data mining and ML methods, and how they can be applied on the edge on user-owned or network devices). He has served in many technical program committees of top conferences and journals (e.g., WWW, KDD, CIKM, ECML-PKDD, TKDD, TKDE, TPDS, etc.), and presented his work in such top academic and industrial venues. His work has been also covered by major news outlets such as Nature, New York Times, The Atlantic, New Scientist, Washington Post, Wired, Vice and others.
