Towards service continuity for transactional applications via diverse device drivers. (2016)

• Record Type: Journal Article
• Authors: Zhang, Shengzhi; Jia, Xiaoqi; Liu, Peng
• Is Part Of: International journal of information and computer security. Volume 8:Number 4(2016)
• Page Start: 382
• Page End: 400
• Publication Date: 2016
• Subjects: intrusion detection -- intrusion response -- transactional applications -- service continuity -- service availability -- virtualisation -- operating system replicas -- driver diversity -- driver code vulnerability -- output validation -- critical memory regions -- persistent data; Computer security -- Periodicals; Information systems management -- Security measures -- Periodicals; Computer networks -- Security measures -- Periodicals; Information technology -- Security measures -- Periodicals; 005.805
• Languages: English
• ISSNs: 1744-1765

Abstract

Existing techniques, such as state roll-back or replay can preserve as much accumulated 'state' as possible when one application is compromised. However, when operating system kernel is compromised, e.g., driver vulnerability exploitation, the default behaviour of most commodity operating systems today is to reboot from a clean initial state. All the running applications also need to be terminated and restarted, thus losing their accumulated 'work in progress' states. In this paper, we propose to leverage virtualisation technique to produce operating system replicas with driver diversity. By replicating transactional application on each replica and loosely synchronising them, we validate the output, critical memory regions and persistent data of transactional applications, thus detecting intrusion stemming from driver code vulnerability. We implement such diversity approach on Xen hypervisor, and rely on a proxy to conduct request replication and response validation. Our evaluation demonstrates that the proposed approach can accurately and immediately detect driver-bug-orientated exploitation and achieve on-the-fly intrusion response to ensure the correctness/continuity of the applications' execution. We only incur 4.44% and 4.7% overhead to response time and CPU respectively in the best case.