IEEE Spectrum, June 23, 2017 – CITRIS Director Costas Spanos is among a team of UC Berkeley researchers investigating the implications – and potential misuse – of information gathered by smart meters. A recent research paper shows that “machine learning systems can be trained to detect occupancy without any initial information from a homeowner.” While this new technology has great potential, the team is also investigating how smart meter information “could be used for home intrusion or other bad activities,” and developing ways to protect homeowner privacy.
“We are now looking to determine the optimal size of the added noise that would mask information about occupancy and still give the utility company an accurate enough reading for its needs,” says Berkeley researcher Ming Jin.
Read the IEEE Spectrum article here.
You can read the published academic paper, “Virtual Occupancy Sensing: Using Smart Meters to Indicate Your Presence,” in IEEE as well.