2 papers
cs.LG2025
Bayesian Robust Aggregation for Federated Learning
Aleksandr Karakulev, Usama Zafar, Salman Toor +1
Federated Learning enables collaborative training of machine learning models on decentralized data. This scheme, however, is vulnerable to adversarial attacks, when some of the cli…
stat.ML2024
Adaptive Robust Learning using Latent Bernoulli Variables
Aleksandr Karakulev, Dave Zachariah, Prashant Singh
We present an adaptive approach for robust learning from corrupted training sets. We identify corrupted and non-corrupted samples with latent Bernoulli variables and thus formulate…