Adversarial training enhances robustness of jet tagging classifiers while preserving performance, with loss surface geometry providing insights into correlations and vulnerability.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
hep-ex 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface
Adversarial training enhances robustness of jet tagging classifiers while preserving performance, with loss surface geometry providing insights into correlations and vulnerability.