TriGuard reports that attribution drift and entropy provide safety insights orthogonal to adversarial accuracy, and that entropy-regularized training reduces this drift.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
TriGuard: Testing Model Safety with Attribution Entropy, Verification, and Drift
TriGuard reports that attribution drift and entropy provide safety insights orthogonal to adversarial accuracy, and that entropy-regularized training reduces this drift.