Florimond Houssiau

Hi! I’m a PhD student in the Computational Privacy Group at Imperial College. I graduated in 2017 with a Master of Engineering in applied mathematics at the Université catholique de Louvain, in Belgium. I studied a range of topics from mathematics to computer science, with a particular focus on discrete math, algorithms, and statistical modelling. I first started working on privacy during an internship at MIT.

Research-wise, I’ve been interested in a range of questions in adversarial privacy, ranging from query obfuscation to protect privacy in Web search queries to large-scale network-based attacks. I interned at Google in 2019, where I worked on differential privacy. I’ve also been a teaching assistant in machine learning and privacy engineering here at Imperial.



  • Gadotti A., Houssiau F., Rocher L., Livshits B., de Montjoye Y. A. (2019) When the signal is in the noise: Exploiting Diffix's Sticky Noise. 28th USENIX Security Symposium (USENIX Security 19).
    Selected Press: TechCrunch, Wall Street Journal
  • Schellekens V., Chatalic A., Houssiau F., de Montjoye Y. A., Jacques L., Gribonval R. (2019) Differentially Private Compressive K-means. ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
  • Houssiau F., Radaelli L., Sapiezynsky P., Shmueli E., de Montjoye Y. A. (2018) Quantifying surveillance in the networked age: Node-based intrusions and group privacy. .