31 citations · 53 across the 18 of their papers we have counts for
Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Empirical Evidence for Simply Connected Decision Regions in Image Classifiers
Arjhun Swaminathan, Mete Akgün
The topology of a classifier's decision regions determines how inputs with the same predicted label can be connected and deformed without changing that prediction. Prior empirical…
cs.CV2025
Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings
Arjhun Swaminathan, Mete Akgün
Deep neural networks for image classification remain vulnerable to adversarial examples -- small, imperceptible perturbations that induce misclassifications. In black-box settings,…
cs.CV2019★ 31 cited
Privacy Preserving Gaze Estimation using Synthetic Images via a Randomized Encoding Based Framework
Efe Bozkir, Ali Burak Ünal, Mete Akgün +2
Eye tracking is handled as one of the key technologies for applications that assess and evaluate human attention, behavior, and biometrics, especially using gaze, pupillary, and bl…