Technical Note: \cal Q-Learning
Machine Learning
Transfer in variable-reward hierarchical reinforcement learning
Machine Learning
WattBot: a residential electricity monitoring and feedback system
CHI '09 Extended Abstracts on Human Factors in Computing Systems
Security and Privacy Challenges in the Smart Grid
IEEE Security and Privacy
ViridiScope: design and implementation of a fine grained power monitoring system for homes
Proceedings of the 11th international conference on Ubiquitous computing
Inferring Personal Information from Demand-Response Systems
IEEE Security and Privacy
IEEE Security and Privacy
IEEE Security and Privacy
Energy theft in the advanced metering infrastructure
CRITIS'09 Proceedings of the 4th international conference on Critical information infrastructures security
Increasing energy awareness through web-enabled power outlets
Proceedings of the 9th International Conference on Mobile and Ubiquitous Multimedia
Multi-vendor penetration testing in the advanced metering infrastructure
Proceedings of the 26th Annual Computer Security Applications Conference
A study on secure wireless networks consisting of home appliances
IEEE Transactions on Consumer Electronics
Hi-index | 0.00 |
Security protection is an integral component for smart homes; however, smart appliances security has received little attention in the research community. Household appliances become very vulnerable if we introduce smart functions without proper security protection. In particular, smart access functions enable users to operate devices remotely. Meanwhile, smart devices are are also designed to support residential demand response, i.e. postpone non-urgent tasks to non-peak hours. However, remote adversaries could utilize such functions to manipulate smart appliances' operations without physically touching them. Such interferences, if not properly handled, could damage the smart devices, disturb owners' life or even harm the households' physical security. In this paper, we present S2A, a security protection solution to be embedded in smart appliances. First, a SUP model is developed to quantify penalties from device security, usability and electricity price. We employ multi-criteria reinforcement learning to integrate the three factors to determine an optimal operation strategy. Next, to leverage the risk of forged control commands or pricing data, we present a realtime assessment mechanism based on Bayesian inference. Risk indices are further integrated into the SUP model to serve as weighting factors of corresponding decision criteria. Evaluation shows that S2A ensures appliances security while providing good usability and economical efficiency.