Can AI Protect Privacy and Still Explain Its Decisions?

When we train models on sensitive data, we often ask how much accuracy we lose by protecting privacy. But what happens to the explanations? This is the question behind our new paper, Pushing the (Decision) Boundaries, with Michael Khavkin and

New paper: Self-Defeating Privacy: Privacy Coins as a Blockchain Liability

We are happy to share that our paper, “Self-Defeating Privacy: Privacy Coins as a Blockchain Liability,” by Danielle Movsowitz Davidow and Eran Toch, has been accepted as a short paper to the 25th Workshop on Privacy in the Electronic Society

Honorable Mention at MuC 2026

Excited to share that the submission, “Beyond Manipulation: How Users Perceive Harmful AI Chatbot Interactions,” by Vanessa Budde and Eran Toch, has received a Short Paper Honorable Mention at MuC 2026! 🏆 The paper is available here. As AI chatbots become

Lecture at Haifa Communications Dept: Kosher Phones

Eran gave a talk at the Communication Department seminar at the University of Haifa, presenting the work by Adam Aviv, Oshrat Ayalon on Kosher phone users’ perceptions of safety, privacy, and community. 

New accepted paper: Differential Privacy Configurations in the Real World: A Comparative Analysis

Exciting news: our paper “Differential Privacy Configurations in the Real World: A Comparative Analysis” was just accepted to IEEE Transactions on Knowledge and Data Engineering. Another great paper of Michael Khavkin‘s Ph.D.! Preprint is available here. Differential Privacy is the

Lest We Forget: Using Machine Learning to Archive October 7 Testimonies

Graduate student Talya Ben Shitrit, advised by Prof. Joachim Meyer from The Department of Industrial Engineering at the The Iby and Aladar Fleischman Faculty of Engineering, are using advanced machine learning methods to process the vast amounts of testimonies from

ISF Grant Awarded: Deep Analysis of Deceptive User Interface Design Patterns

We are very happy to share that the lab was awarded an ISF grant for the Deep Analysis of Deceptive User Interface Design Patterns. The goal of this project is to develop robust methods for identifying deceptive patterns (also known