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.
Learning transferable visual models from natural language supervision,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 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.