Solver-integrated PGD attacks produce stronger adversarial examples for neural operators than dictionary-based attacks, and round-based retraining improves some out-of-distribution accuracy but with mixed, costly results.
Giometto, Marc B
1 Pith paper cite this work, alongside 18 external citations. Polarity classification is still indexing.
1
Pith paper citing it
18
external citations · OpenAlex
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Solver-Integrated Adversarial Attacking and Training of Neural Operators
Solver-integrated PGD attacks produce stronger adversarial examples for neural operators than dictionary-based attacks, and round-based retraining improves some out-of-distribution accuracy but with mixed, costly results.