RepEL: A Utility-Preserving Privacy System for IoT-Based Energy Meters

Bovornkeeratiroj, Phuthipong; Iyengar, S. S.; Lee, Stephen; Irwin, David; Shenoy, Prashant

doi:10.1109/iotdi49375.2020.00015

Cited by 11 publications

(7 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LogSafe is a a scalable, fault-tolerant logger that leverages the use of Intel Software Guard Extensions (SGX) to store logs from IoT devices efficiently and securely [11]. RepEl [12] proposes a utility-preserving privacy technique, which intelligently obfuscates smart energy meter data to prevent leaking a home's private occupancy information, while retaining the ability to perform useful energy disaggregation analytics. Kim et.…”

Section: Related Workmentioning

confidence: 99%

BULWARK: A Framework to Store IoT Data in User Accounts

Reed

Tosun

2022

IEEE Access

View full text Add to dashboard Cite

The explosive growth of the Internet of Things (IoT) devices raises serious concerns for a user's privacy and security because the existing software framework on these devices often support various default features and generate large data sets. Moreover, many IoT devices incorporate a manufacturer-owned cloud-based back-end support to process and store the generated data while simultaneously sharing with third parties. Clearly, in such an industry-driven environment with the desire to use the IoT data as a revenue stream, it is a challenge for users to control IoT data. Device manufacturers utilize an opaque software design where user data is generated and stored with little transparency. Manufacturers use EULAs as a legal construct to protect a manufacturer's legal standing and to explain a device's behavior, however this explanation is vague and lacks the necessary details for a user to determine a device's acceptable use and it has become increasingly difficult for users to secure and maintain their data. Fortunately, as the privacy minded user base of IoT devices grows, the manufacturers will be forced to implement a new framework that can enable users to have more control on the creation of their IoT data, and to store/disseminate such data in a secure and private manner. In this paper, we address this lack of transparency from manufacturers and address the issues of privacy and security by proposing a new framework called Bulwark, for manufacturer use on IoT devices and mobile applications. Proposed framework enables the user to generate and manage a set of data controlling rules, and store the result in their personal cloud account, while providing a dashboard data reporting tool enabling data transparency and supporting good user choices. The user's ability to access, disseminate and secure IoT generated data, is now available within our proposed framework. Using reverse engineering, simulation and implementation of open source solutions, we demonstrate support for a set of common devices. Each device executed the framework, while communicating with a mobile application and cloud services. Rules were generated for each message and telemetry was returned to the mobile application for dashboard rendering. We stored generated data in the cloud using our own account, while maintaining the free tier for each of the cloud services. Network usage increased between 4% and 9% while storage size grew between 0% and 2% larger, as compared to using the device without the framework. Our framework demonstrates support for a multitude of devices, by either open source or support for similar feature sets. This framework is easy to integrate and we anticipate wide spread adoption.

show abstract

Section: Related Workmentioning

confidence: 99%

BULWARK: A Framework to Store IoT Data in User Accounts

Reed

Tosun

2022

IEEE Access

View full text Add to dashboard Cite

show abstract

“…These types of cameras rely on a two-tier cloud-based architecture, where the video is transmitted over the Internet for analytics processing in the cloud. The two-tier architecture also enables remote access to the cameras over the Internet [5]. This is the basic architecture assumed in our work (see Figure1).…”

Section: Smart Camerasmentioning

confidence: 99%

Energy-Efficient Parking Analytics System using Deep Reinforcement Learning

Rezaei,

Lee,

Mosse

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Advances in deep vision techniques and ubiquity of smart cameras will drive the next generation of video analytics. However, video analytics applications consume vast amounts of energy as both deep learning techniques and cameras are power-hungry. In this paper, we focus on a parking video analytics platform and propose RL-CamSleep, a deep reinforcement learning-based technique, to actuate the cameras to reduce the energy footprint while retaining the system's utility. Our key insight is that many video-analytics applications do not always need to be operational, and we can design policies to activate video analytics only when necessary. Moreover, our work is complementary to existing work that focuses on improving hardware and software efficiency. We evaluate our approach on a city-scale parking dataset having 76 streets spread across the city. Our analysis demonstrates how streets have various parking patterns, highlighting the importance of an adaptive policy. Our approach can learn such an adaptive policy that can reduce the average energy consumption by 76.38% and achieve an average accuracy of more than 98% in performing video analytics.

show abstract

“…However, previous studies have observed that for high-dimensional time series data, DP often adds too much noise that can lead to unsatisfactory data utility [12,14]. BLH has been proposed in [2,20]. The goal of BLH is to install a battery at the consumer end, which can be charged or discharged to make the electricity meter incapable of precisely obtaining the consumption data of electric appliances and to obfuscate the actual consumption of the electric appliances [25].…”

Section: Related Workmentioning

confidence: 99%

“…Battery-based load hiding (BLH) has been proposed in [2,20]. The goal of BLH approach is to mask smart meter reading by utilizing a rechargeable battery.…”

Section: Introductionmentioning

confidence: 99%

DFTMicroagg: a dual-level anonymization algorithm for smart grid data

Adewole

Torra

2022

Int. J. Inf. Secur.

View full text Add to dashboard Cite

The introduction of advanced metering infrastructure (AMI) smart meters has given rise to fine-grained electricity usage data at different levels of time granularity. AMI collects high-frequency daily energy consumption data that enables utility companies and data aggregators to perform a rich set of grid operations such as demand response, grid monitoring, load forecasting and many more. However, the privacy concerns associated with daily energy consumption data has been raised. Existing studies on data anonymization for smart grid data focused on the direct application of perturbation algorithms, such as microaggregation, to protect the privacy of consumers. In this paper, we empirically show that reliance on microaggregation alone is not sufficient to protect smart grid data. Therefore, we propose DFTMicroagg algorithm that provides a dual level of perturbation to improve privacy. The algorithm leverages the benefits of discrete Fourier transform (DFT) and microaggregation to provide additional layer of protection. We evaluated our algorithm on two publicly available smart grid datasets with millions of smart meters readings. Experimental results based on clustering analysis using k-Means, classification via k-nearest neighbor (kNN) algorithm and mean hourly energy consumption forecast using Seasonal Auto-Regressive Integrated Moving Average with eXogenous (SARIMAX) factors model further proved the applicability of the proposed method. Our approach provides utility companies with more flexibility to control the level of protection for their published energy data.

show abstract

RepEL: A Utility-Preserving Privacy System for IoT-Based Energy Meters

Cited by 11 publications

References 22 publications

BULWARK: A Framework to Store IoT Data in User Accounts

BULWARK: A Framework to Store IoT Data in User Accounts

Energy-Efficient Parking Analytics System using Deep Reinforcement Learning

DFTMicroagg: a dual-level anonymization algorithm for smart grid data

Contact Info

Product

Resources

About