Zero-day attacks exploit undisclosed vulnerabilities rather than novel behaviors, so vulnerability-centric detection aligns better with real incidents than behavior-focused ML approaches.
Guo, A review of machine learning-based zero-day attack detection: Challenges and future directions
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CR 3verdicts
UNVERDICTED 3representative citing papers
Hybrid feature fusion of API calls and n-grams with voting-based classifier fusion achieves 99.72% accuracy and 0.989 AUC for malware family classification on Microsoft dataset.
A lightweight CNN classifies packet flows from CIC-DDoS2019 as benign or malicious with 0.9883 accuracy, 0.9824 F1, and 0.28-second test-set processing time.
citing papers explorer
-
Zero Day Attacks: Novel Behaviour or Novel Vulnerability?
Zero-day attacks exploit undisclosed vulnerabilities rather than novel behaviors, so vulnerability-centric detection aligns better with real incidents than behavior-focused ML approaches.
-
A Hybrid Approach For Malware Classification Using Secondary Features Fusion
Hybrid feature fusion of API calls and n-grams with voting-based classifier fusion achieves 99.72% accuracy and 0.989 AUC for malware family classification on Microsoft dataset.
-
Lightweight CNN-Based DDoS Detection for Resource-Constrained Edge Networks
A lightweight CNN classifies packet flows from CIC-DDoS2019 as benign or malicious with 0.9883 accuracy, 0.9824 F1, and 0.28-second test-set processing time.