2 papers
cs.CR2025
Model-agnostic clean-label backdoor mitigation in cybersecurity environments
Giorgio Severi, Simona Boboila, John Holodnak +4
The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks tha…
cs.LG2024
ScatterUQ: Interactive Uncertainty Visualizations for Multiclass Deep Learning Problems
Harry Li, Steven Jorgensen, John Holodnak +1
Recently, uncertainty-aware deep learning methods for multiclass labeling problems have been developed that provide calibrated class prediction probabilities and out-of-distributio…