David Evans

Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization

2020 · arXiv (Cornell University)

Training machine learning models that are robust against adversarial inputs poses seemingly insurmountable challenges. To better understand adversarial robustness, we consider the underlying problem of learning robust representations. We develop a notion of representation vulnerability …

OPSSAT-AD - anomaly detection dataset for satellite telemetry

2024 · arXiv (Cornell University)

Detecting anomalous events in satellite telemetry is a critical task in space operations. This task, however, is extremely time-consuming, error-prone and human dependent, thus automated data-driven anomaly detection algorithms have been emerging at a steady …