Search Results for author:
Found 4 papers, 3 papers with code
Model Selection of Zero-shot Anomaly Detectors in the Absence of Labeled Validation Data
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.
Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning
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.
Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting
Distributed machine learning (ML) systems today use an unsophisticated threat model: data sources must trust a central ML process.
Mitigating Sybils in Federated Learning Poisoning
Unfortunately, such approaches are susceptible to a variety of attacks, including model poisoning, which is made substantially worse in the presence of sybils.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
