Collapsar: A VM-based honeyfarm and reverse honeyfarm architecture for network attack capture and detention

The honeypot has emerged as an effective tool to provide insights into new attacks and exploitation trends. However, a single honeypot or multiple independently operated honeypots only provide limited local views of network attacks. Coordinated deployment of honeypots in different network domains not only provides broader views, but also create opportunities of early network anomaly detection, attack correlation, and global network status inference. Unfortunately, coordinated honeypot operation require close collaboration and uniform security expertise across participating network domains. The conflict between decentralized presence and uniform management poses a major challenge in honeypot deployment and operation. To address this challenge, we present Collapsar, a virtual machine based architecture for network attack capture and detention. A Collapsar center hosts and manages a large number of high-interaction virtual honeypots in a local dedicated network. To attackers, these honeypots appear as real systems in their respective production networks. Decentralized logical presence of honeypots provides a wide diverse view of network attacks, while the centralized operation enables dedicated administration and convenient event correlation, eliminating the need for honeypot expertise in every production network domain. Collapsar realizes the traditional honeyfarm vision as well as our new reverse honeyfarm vision, where honeypots act as vulnerable clients exploited by real-world malicious servers. We present the design, implementation, and evaluation of a Collapsar prototype. Our experiments with a number of real-world attacks demonstrate the effectiveness and practicality of Collapsar.