2 papers
cs.LG2026
Mitigating Black-Box Score-Based Query Attacks via Gradient Confusion
Ali Javeri, Javad Hezareh, Radin Shahdaei +1
Score-based black-box adversarial attacks pose a serious threat to deployed machine learning systems by exploiting repeated model queries to craft adversarial examples, requiring n…
cs.LG2025
Budget Allocation for Unknown Value Functions in a Lipschitz Space
MohammadHossein Bateni, Hossein Esfandiari, Samira HosseinGhorban +2
Building learning models frequently requires evaluating numerous intermediate models. Examples include models considered during feature selection, model structure search, and param…