Posts by Collection

This is probably my favorite presentation that I have made. It was 2022, it was a paper of mine I really liked, and I had just bought an iPad and was very excited to use it for a presentation. I really like the first and last slides:

This is the 2024 version of my general-purpose drawings, the ones I use across talks, papers, and course slides. It is slightly outdated, hopefully will update at some point.

My colleague Bailey Kacsmar was co-chairing PETS 2026 with Ryan Henry, and she suggested the idea that I could draw a “mascot” for the conference.

Link to the course syllabus for 2026W1.

The following is some public content for 2026W1, for students that do not yet have access to Canvas:

Co-instructor with Prof. Yousra Aafer. Link to course material and syllabus.

Nowadays, most Internet communications are encrypted, which is great! However, even if your data is encrypted, it is not hard for an adversary to tell where your traffic is going (e.g., that particular website you are visiting). To hide who talks with whom over the Internet (and other meta-data), we need anonymous communications systems. Tor is the most successful of such systems, but there is another type of systems, less known, called mixnets. Mixnets aim to protect against a global passive adversary, which is something that even Tor cannot do. While mixnets were conceived a long time ago, their deployments are very recent.

Open your phone, got to location permissions, and see how many apps you are sharing your location with. Probably a lot. Food delivery, rideshare, weather forecast, camera, dating apps, etc. To use most of these apps, we need to share our location data with a service provider. Have you ever wondered how sensitive this information is? With your location information is not only trivial to learn where you live and work, but one could probably infer your hobbies, habits, political preferences, etc. What if the service provider is malicious or does not have the proper safeguards to protect your data? Scary!

Machine learning technologies are everywhere. Here’s the privacy angle of all this: when one builds a machine learning model using a privacy-sensitive training dataset, the model will memorize some privacy-sensitive information. An attacker with access to that model (even if it is just black-box query access) can learn a lot of information about the training data. The most basic attack in this setting is called membership inference attack, where an attacker gets access to a model and a data sample, and wants to guess whether that sample was in the model’s training set. More complex attacks include model inversion, where the attacker reconstructs training samples just by querying the model! Sadly, due to the complexity of machine learning (it’s called machine learning, after all), preventing these attacks is really hard!

Storing data in the cloud is very convenient: it frees resources on our local devices and provides data availability as long as we have an Internet connection. However, storing privacy-sensitive data in the cloud is somewhat scary: what if the cloud is looking at our data? Can we trust the cloud?