How does web-based malware spread? We use the term web-based malware to describe malware that is distributed through websites, and malicious posts in social networks. We are in an arms race against web-based malware distributors; and as in any war, knowledge is power. The more we know about them, the better we can defend ourselves. Our goal is to understand the dissemination of web-based malware by creating "MalScope", a suite of methods and tools that uses cutting-edge approaches to build spatiotemporal models, generators and sampling techniques for malware dissemination. From a scientific point of view, this project brings together two disciplines: Data Mining and Network Security. The outcome is a suite of novel, sophisticated, and scalable techniques and models that will enhance our understanding of malware dissemination at a large scale. We use two types of web-based malware dissemination data: (1) user machines accessing dangerous sites and downloading web-based malware; and (2) Facebook users being exposed to malicious posts. We already have and will continue to obtain more data from our industry partners (e.g. Symantec's WINE project), open-access projects, or collect on our own (e.g MyPageKeeper).
The broader impact of our work is that it will enable the development of security solutions for end-users and industry. A 15-minute network outage costs a 200-employee company about $40K, while identity theft costs about $1,500 per person on average. By knowing the enemy better, security researchers and industry can more effectively stop the interconnected manifestations of Internet threats: identity theft, the creation of botnets, and DoS attacks. The PIs have a track record of technology transfer, with collaborators at industrial labs (Yahoo, MSR, Symantec, AT&T, IBM), national labs (LLNL, Sandia), open-source software (``Pegasus''), and spin-off startups (StopTheHacker). Educational impacts include developing a new course, providing publicly available educational material, and open-source software.
