On NSL-KDD, between 19.7% and 76.2% of adversarial examples from common attacks violate the paper's network constraints, and filtering them to feasible inputs sharply lowers measured attack severity on several classifiers.
Insomnia: Towards concept-drift robustness in network intrusion detection,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Constrained Network Adversarial Attacks: Validity, Robustness, and Transferability
On NSL-KDD, between 19.7% and 76.2% of adversarial examples from common attacks violate the paper's network constraints, and filtering them to feasible inputs sharply lowers measured attack severity on several classifiers.