Abstract
This paper studies the feasibility of an early warning system that prevents users from the dangerous situations they may fall into during web surfing. Our approach adopts behavioral Hidden Markov Models to explore collective intelligence embedded in users' browsing behaviors for context-aware category prediction, and applies the results to web security threat prevention. Largescale experiments show that our proposed method performs accuracy 0.463 for predicting the fine-grained categories of users' next accesses. In real-life filtering simulations, our method can achieve macro-averaging blocking rate 0.4293 to find web security threats that cannot be detected by the existing security protection solutions at the early stage, while accomplishes a low macro-averaging over-blocking rate 0.0005 with the passage of time. In addition, behavioral HMM is able to alert users for avoiding security threats by 8.4 hours earlier than the current URL filtering engine does. Our simulations show that the shortening of this lag time is critical to avoid severe diffusions of security threats.
Original language | English |
---|---|
Title of host publication | CCS'12 - Proceedings of the 2012 ACM Conference on Computer and Communications Security |
Pages | 992-994 |
Number of pages | 3 |
DOIs | |
Publication status | Published - 2012 |
Event | 2012 ACM Conference on Computer and Communications Security, CCS 2012 - Raleigh, NC, United States Duration: 2012 Oct 16 → 2012 Oct 18 |
Other
Other | 2012 ACM Conference on Computer and Communications Security, CCS 2012 |
---|---|
Country | United States |
City | Raleigh, NC |
Period | 2012/10/16 → 2012/10/18 |
Keywords
- Collaborative filtering
- Collective intelligence
- Security assurance
ASJC Scopus subject areas
- Software
- Computer Networks and Communications