86 citations · 387 across the 45 of their papers we have counts for
6 papers · 1 filter
Janus: Safe Biometric Deduplication for Humanitarian Aid Distribution
Kasra EdalatNejad, Wouter Lueks, Justinas Sukaitis +3
Humanitarian organizations provide aid to people in need. To use their limited budget efficiently, their distribution processes must ensure that legitimate recipients cannot receiv…
Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings
Klim Kireev, Maksym Andriushchenko, Carmela Troncoso +1
Research on adversarial robustness is primarily focused on image and text data. Yet, many scenarios in which lack of robustness can result in serious risks, such as fraud detection…
Can Decentralized Learning be more robust than Federated Learning?
Mathilde Raynal, Dario Pasquini, Carmela Troncoso
Decentralized Learning (DL) is a peer--to--peer learning approach that allows a group of users to jointly train a machine learning model. To ensure correctness, DL should be robust…
Not Yet Another Digital ID: Privacy-preserving Humanitarian Aid Distribution
Boya Wang, Wouter Lueks, Justinas Sukaitis +2
Humanitarian aid-distribution programs help bring physical goods to people in need. Traditional paper-based solutions to support aid distribution do not scale to large populations…
Arbitrary Decisions are a Hidden Cost of Differentially Private Training
Bogdan Kulynych, Hsiang Hsu, Carmela Troncoso +1
Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomizat…
Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data
Dario Pasquini, Giuseppe Ateniese, Carmela Troncoso
We introduce the concept of "universal password model" -- a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achi…