Mal-D2GAN, a GAN with two detectors and a least-squares loss, produced adversarial malware that lowered the true positive rate of eight classifiers to near zero on a 20,000-sample dataset.
Generating adversarial malware examples for black-box attacks based on gan,
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
-
Mal-D2GAN: Double-Detector based GAN for Malware Generation
Mal-D2GAN, a GAN with two detectors and a least-squares loss, produced adversarial malware that lowered the true positive rate of eight classifiers to near zero on a 20,000-sample dataset.