New OCSVM method improves malware classification model retraining efficiency

A new research paper explores methods for detecting and adapting to concept drift in malware classification models. The study analyzes two primary techniques: one based on One-Class Support Vector Machines (OCSVM) and another using Minibatch K-Means (MK-Means), also considering Maximum Mean Discrepancy (MMD). Experiments with Multilayer Perceptron, Random Forest, Support Vector Machines, and XGBoost models show that drift-aware retraining, particularly with the OCSVM approach, achieves comparable accuracy to periodic retraining but with significantly greater efficiency. AI

IMPACT Improves efficiency and accuracy of malware classification models by enabling smarter retraining strategies.

RANK_REASON Research paper published on arXiv detailing new methods for concept drift detection in machine learning models. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• Maximum Mean Discrepancy
• Minibatch K-Means
• Multilayer Perceptron
• OCSVM
• ONE-CLASS SUPPORT VECTOR MACHINES APPROACH TO ANOMALY DETECTION
• Random Forest
• William Andreopoulos
• XGBoost

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →