Neurons that respond abnormally to adversarial inputs are concentrated in early ViT layers, and suppressing them with a fixed mask improves robustness across attacks without retraining.
Multimodal learning with transform- ers: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Mechanistic Understandings of Representation Vulnerabilities and Engineering Robust Vision Transformers
Neurons that respond abnormally to adversarial inputs are concentrated in early ViT layers, and suppressing them with a fixed mask improves robustness across attacks without retraining.