A3 is a learnable activation scaling module that trains on amplified adversarial signals via contrastive losses to improve robustness when the same parameters are used in attenuation mode.
arXiv preprint arXiv:2503.08023 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Adversarial Robustness via Activation Amplification and Attenuation
A3 is a learnable activation scaling module that trains on amplified adversarial signals via contrastive losses to improve robustness when the same parameters are used in attenuation mode.