Adversarial Robustness of Self-Supervised Learning Features

As deep learning models have proliferated, concerns about their reliability and security have also increased. One significant challenge is understanding adversarial perturbations, which can alter a model's predictions despite being very small in magnitude. Prior work has proposed that this phen...

Full description

Saved in:
Bibliographic Details
Main Authors: Nicholas Mehlman, Shri Narayanan
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Open Journal of Signal Processing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10971198/
Tags: Add Tag
No Tags, Be the first to tag this record!