作者: Joshua Schiffman , Yuqiong Sun , Hayawardh Vijayakumar , Trent Jaeger
关键词:
摘要: Cloud computing has commoditized compute, storage, and networking resources creating an on-demand utility. Despite the attractiveness of this new paradigm, its adoption been stymied by cloud platform's lack transparency, which leaves customers unsure if their sensitive data computation can be entrusted to cloud. While techniques like encryption protect customers' at rest, clouds still mechanisms for verify that computations are being executed as expected, a guarantee one could obtain they were running in own center. In paper, we present verifier (CV), flexible framework vendors configure provide monitoring services validate configured run expected Infrastructure Service (IaaS) clouds. The CV builds chain trust from customer hosted virtual machine (VM) instances through platform, enabling it check customer-specified requirements against comprehensive view both VM's load-time run-time properties. addition, enables more responsive remediation than traditional attestation mechanisms. We built proof concept OpenStack platform whose evaluation demonstrates single over 20,000 simultaneous numerous properties with little impact on application performance. As result, gives low-overhead method assuring according requirements.