Byzantine machine learning: A primer
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, consists of designing distributed algorithms that can train an accurate model …
Recent advances in algorithmic high-dimensional robust statistics
I Diakonikolas, DM Kane - arXiv preprint arXiv:1911.05911, 2019 - arxiv.org
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 …
known efficient unsupervised learning algorithms were very sensitive to outliers in high …
Privacy and robustness in federated learning: Attacks and defenses
As data are increasingly being stored in different silos and societies becoming more aware
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …
of data privacy issues, the traditional centralized training of artificial intelligence (AI) models …
Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses
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 …
practitioners to automate and outsource the curation of training data in order to achieve state …
Byzantine machine learning made easy by resilient averaging of momentums
Byzantine resilience emerged as a prominent topic within the distributed machine learning
community. Essentially, the goal is to enhance distributed optimization algorithms, such as …
community. Essentially, the goal is to enhance distributed optimization algorithms, such as …
Robust estimators in high-dimensions without the computational intractability
We study high-dimensional distribution learning in an agnostic setting where an adversary is
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …
allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history …
Robust federated learning in a heterogeneous environment
We study a recently proposed large-scale distributed learning paradigm, namely Federated
Learning, where the worker machines are end users' own devices. Statistical and …
Learning, where the worker machines are end users' own devices. Statistical and …
Sever: A robust meta-algorithm for stochastic optimization
In high dimensions, most machine learning methods are brittle to even a small fraction of
structured outliers. To address this, we introduce a new meta-algorithm that can take in a …
structured outliers. To address this, we introduce a new meta-algorithm that can take in a …
Stronger data poisoning attacks break data sanitization defenses
Abstract Machine learning models trained on data from the outside world can be corrupted
by data poisoning attacks that inject malicious points into the models' training sets. A …
by data poisoning attacks that inject malicious points into the models' training sets. A …
Statistical, robustness, and computational guarantees for sliced wasserstein distances
Sliced Wasserstein distances preserve properties of classic Wasserstein distances while
being more scalable for computation and estimation in high dimensions. The goal of this …
being more scalable for computation and estimation in high dimensions. The goal of this …