Whitepaper called Nazca: Detecting Malware Distribution in Large-Scale Networks. In this paper, they study how clients in real-world networks download and install malware, and present Nazca, a system that detects infections in large scale networks. Nazca does not operate on individual connections, nor looks at properties of the downloaded programs or the reputation of the servers hosting them. Instead, it looks at the telltale signs of the malicious network infrastructures that orchestrate these malware installation that become apparent when looking at the collective traffic produced and becomes apparent when looking at the collective traffic produced by many users in a large network. Being content agnostic, Nazca does not suffer from coverage gaps in reputation databases (blacklists), and is not susceptible to code obfuscation. They have run Nazca on seven days of traffic from a large Internet Service Provider, where it has detected previously-unseen malware with very low false positive rates.
032e0a68647df30e19b1e6384d3777c89aaa648d1c9fa02c224a00ccae04a680