McPAD: A multiple classifier system for accurate payload-based anomaly detection

293 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Practical Evasion of a Learning-Based Classifier: A Case Study (2014, background): “Some applications of multiple classifier systems in security and other adversarial scenarios have recently been considered [46], [47].”
Toward Supervised Anomaly Detection (2014, methodology): “To study the robustness of our approach in a more realistic scenario, we also consider techniques to obfuscate malicious content by adapting attack payloads to mimic benign trafﬁc in feature space (Fogla, Sharif, Perdisci, Kolesnikov, & Lee, 2006; Perdisci et al., 2009).”
A comprehensive survey on machine learning for networking: evolution, applications and research opportunities (2018, methodology): “[356] Supervised Ensemble of single-class SVM (Offline) Normal: KDD Cup [257] Normal: GATECH Attack: CLET [117] Attack: PBA [149] Generic [204] Payload -50% of dataset for training -50% of dataset for testing -11 OCSVM trained with 2v-grams; v=1.”
Network Anomaly Detection: Methods, Systems and Tools (2014, methodology): “tion) [183] is an effective payload-based anomaly detection”