Exciting news! Our recent paper, "Cross-Network Embeddings Transfer for Traffic Analysis," featured in IEEE Transactions on Network and Service Management, introduces innovative approaches to enhance traffic analysis using artificial intelligence (AI). We address the challenge of limited labeled datasets and dynamic networking environments by proposing techniques to transfer knowledge between different networks. By aligning embeddings and leveraging transfer learning methods, our research facilitates the adoption of AI-based solutions for traffic analysis and cybersecurity. Through comprehensive experimental analysis, we demonstrate the effectiveness of our approach in both supervised and unsupervised tasks related to darknet and honeypot traffic. This work paves the way for collaborative knowledge sharing between network providers and customers, leading to improved network intelligence and management. Explore our paper for insights into advancing network analytics through cross-network knowledge transfer

Abstract

Artificial Intelligence (AI) approaches have emerged as powerful tools to improve traffic analysis for network monitoring and management. However, the lack of large labeled datasets and the ever-changing networking scenarios make a fundamental difference compared to other domains where AI is thriving. We believe the ability to transfer the specific knowledge acquired in one network (or dataset) to a different network (or dataset) would be fundamental to speed up the adoption of AI-based solutions for traffic analysis and other networking applications (e.g., cybersecurity). We here propose and evaluate different options to transfer the knowledge built from a provider network, owning data and labels, to a customer network that desires to label its traffic but lacks labels. We formulate this problem as a domain adaptation problem that we solve with embedding alignment techniques and canonical transfer learning approaches. We present a thorough experimental analysis to assess the performance considering both supervised (e.g., classification) and unsupervised (e.g., novelty detection) downstream tasks related to darknet and honeypot traffic. Our experiments show the proper transfer techniques to use the models obtained from a network in a different network. We believe our contribution opens new opportunities and business models where network providers can successfully share their knowledge and AI models with customers. 

Keywords:  Darknets, network monitoring, transfer learning, representation learning, domain adaptation.

Authors: L. Gioacchini, M. Mellia, L. Vassio, I. Drago, G. Milan, Z. B. Houidi, and D. Rossi

Available on https://ieeexplore.ieee.org/abstract/document/10304313