Paper ID: 2206.06761 • Published Jun 14, 2022

Exploring Adversarial Attacks and Defenses in Vision Transformers trained with DINO

Javier Rando, Nasib Naimi, Thomas Baumann, Max Mathys
TL;DR
Get AI-generated summaries with premium
Get AI-generated summaries with premium
This work conducts the first analysis on the robustness against adversarial attacks on self-supervised Vision Transformers trained using DINO. First, we evaluate whether features learned through self-supervision are more robust to adversarial attacks than those emerging from supervised learning. Then, we present properties arising for attacks in the latent space. Finally, we evaluate whether three well-known defense strategies can increase adversarial robustness in downstream tasks by only fine-tuning the classification head to provide robustness even in view of limited compute resources. These defense strategies are: Adversarial Training, Ensemble Adversarial Training and Ensemble of Specialized Networks.