no code implementations • 16 Oct 2023 • Clement Fung, Chen Qiu, Aodong Li, Maja Rudolph
In this work, we propose SWSA (Selection With Synthetic Anomalies): a general-purpose framework to select image-based anomaly detectors with a generated synthetic validation set.
2 code implementations • 24 Nov 2018 • Muhammad Shayan, Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh
Federated Learning is the current state of the art in supporting secure multi-party machine learning (ML): data is maintained on the owner's device and the updates to the model are aggregated through a secure protocol.
1 code implementation • 23 Nov 2018 • Clement Fung, Jamie Koerner, Stewart Grant, Ivan Beschastnikh
Distributed machine learning (ML) systems today use an unsophisticated threat model: data sources must trust a central ML process.
2 code implementations • 14 Aug 2018 • Clement Fung, Chris J. M. Yoon, Ivan Beschastnikh
Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils.