A post-training defense that linearizes and merges fully connected layers reduces Trojan attack success rate on Vision Transformers while compressing the model.
Machine learning for quantitative finance applications: A survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MergeGuard: Efficient Thwarting of Trojan Attacks in Machine Learning Models
A post-training defense that linearizes and merges fully connected layers reduces Trojan attack success rate on Vision Transformers while compressing the model.