The problem of Byzantine resilience in distributed machine learning, aka Byzantine machine
learning, consists of designing distributed algorithms that can train an accurate model …

Learning in the presence of outliers is a fundamental problem in statistics. Until recently, all
known efficient unsupervised learning algorithms were very sensitive to outliers in high …

Data-centric AI is at the center of a fundamental shift in software engineering where machine
learning becomes the new software, powered by big data and computing infrastructure …

We propose the first fast and certifiable algorithm for the registration of two sets of three-
dimensional (3-D) points in the presence of large amounts of outlier correspondences. A …

We study the problem of unlearning datapoints from a learnt model. The learner first
receives a dataset $ S $ drawn iid from an unknown distribution, and outputs a model …

A recent line of work has uncovered a new form of data poisoning: so-called backdoor
attacks. These attacks are particularly dangerous because they do not affect a network's …

We present a novel approach to federated learning that endows its aggregation process with
greater robustness to potential poisoning of local data or model parameters of participating …

In this paper, we develop distributed optimization algorithms that are provably robust against
Byzantine failures—arbitrary and potentially adversarial behavior, in distributed computing …

As machine learning systems grow in scale, so do their training data requirements, forcing
practitioners to automate and outsource the curation of training data in order to achieve state …

Abstract Machine learning systems trained on user-provided data are susceptible to data
poisoning attacks, whereby malicious users inject false training data with the aim of …