3 papers
cs.LG2025
Adversarial Surrogate Risk Bounds for Binary Classification
Natalie S. Frank
A central concern in classification is the vulnerability of machine learning models to adversarial attacks. Adversarial training is one of the most popular techniques for training…
cs.LG2025
A Notion of Uniqueness for the Adversarial Bayes Classifier
Natalie S. Frank
We propose a new notion of uniqueness for the adversarial Bayes classifier in the setting of binary classification. Analyzing this concept produces a simple procedure for computing…
cs.LG2024
Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier
Natalie S. Frank
Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in t…