When Machine Learning Models Leak: An Exploration of Synthetic Training Data

We investigate an attack on a machine learning classifier that predicts the propensity of a person or household to move (i.e., relocate) in the next two years. The attack assumes that the classifier has been made publically available and that the attacker has access to information about a certain number of target individuals. That attacker...

Machine Learning Meets Data Modification: The Potential of Pre-processing for Privacy Enchancement

We explore how data modification can enhance privacy by examining the connection between data modification and machine learning. Specifically, machine learning “meets” data modification in two ways. First, data modification can protect the data that is used to train machine learning models focusing it on the intended use and inhibiting...

Towards user-oriented privacy for recommender system data: A personalization-based approach to gender obfuscation for user profiles

In this paper, we propose a new privacy solution for the data used to train a recommender system, i.e., the user–item matrix. The user–item matrix contains implicit information, which can be inferred using a classifier, leading to potential privacy violations. Our solution, called Personalized Blurring (PerBlur), is a simple, yet effective,...

SimuRec: Workshop on synthetic data and simulation methods for recommender systems research

There is significant interest lately in using synthetic data and simulation infrastructures for various types of recommender systems research. However, there are not currently any clear best practices around how best to apply these methods. We proposed a workshop to bring together researchers and practitioners interested in simulating...

BlUrM(or)e: Revisiting gender obfuscation in the user-item matrix

Past research has demonstrated that removing implicit gender information from the user-item matrix does not result in substantial performance losses. Such results point towards promising solutions for protecting users’ privacy without compromising prediction performance, which are of particular interest in multistakeholder environments. Here,...

Data masking for recommender systems: Prediction performance and rating hiding

Data science challenges allow companies, and other data holders, to collaborate with the wider research community. In the area of recommender systems, the potential of such challenges to move forward the state of the art is limited due to concerns about releasing user interaction data. This paper investigates the potential of privacy...

Up close, but not too personal: Hypotargeting for recommender systems

Hypotargeting for recommender systems (hyporec) is the idea of controlling the number of unique lists of items that a recommender system can recommend to users during a given time period. The main advantage of hyporec is oversight. If a recommender system offers only a finite number of unique lists, then it becomes feasible for a person...