Adversarial Robustness of Vision Transformers, MLP-Mixer, and CNNs on ImageNet-1K

This report synthesises findings from 14 peer-reviewed papers addressing the following research question: How does the adversarial robustness of Multi-Head Self-Attention (MHSA) in Vision Transformers compare to that of MLP-Mixer and CNNs when evaluated under targeted perturbations on ImageNet-1K. In this paper, we ask whether Vision Transformers (ViTs) can serve as an underlying architecture for improving the adversarial robustness of machine learning models against evasion attacks. While earlier works have focused on improving Convolutional Neural Networks, we show that. 8 claims were extracted from source literature; 8 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 8.3/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does the adversarial robustness of Multi-Head Self-Attention (MHSA) in Vision Transformers compare to that of MLP-Mixer and CNNs when evaluated under targeted perturbations on ImageNet-1K?

Autonomous literature synthesis. Automated review score: 8.3/10. Full text and citation available at Assignee Research.