18 August 2020 in IEEE Internet of Things Journal
Home appliance manufacturers strive to obtain feedback from users to improve their products and services to build a smart home system. To help manufacturers develop a smart home system, we design a federated learning (FL) system leveraging a reputation mechanism to assist home appliance manufacturers to train a machine learning model based on customers’ data. Then, manufacturers can predict customers’ requirements and consumption behaviors in the future. The working flow of the system includes two stages: in the first stage, customers train the initial model provided by the manufacturer using both the mobile phone and the mobile edge computing (MEC) server. Customers collect data from various home appliances using phones, and then they download and train the initial model with their local data. After deriving local models, customers sign on their models and send them to the blockchain. In case customers or manufacturers are malicious, we use the blockchain to replace the centralized aggregator in the traditional FL system. Since records on the blockchain are untampered, malicious customers or manufacturers’ activities are traceable. In the second stage, manufacturers select customers or organizations as miners for calculating the averaged model using received models from customers. By the end of the crowdsourcing task, one of the miners, who is selected as the temporary leader, uploads the model to the blockchain. To protect customers’ privacy and improve the test accuracy, we enforce differential privacy on the extracted features and propose a new normalization technique. We experimentally demonstrate that our normalization technique outperforms batch normalization when features are under differential privacy protection. In addition, to attract more customers to participate in the crowdsourcing FL task, we design an incentive mechanism to award participants.
1 March 2017 in IEEE Transactions on Information Forensics and Security
This paper studies the impact of false data injection (FDI) attacks on automatic generation control (AGC), a fundamental control system used in all power grids to maintain the grid frequency at a nominal value. Attacks on the sensor measurements for AGC can cause frequency excursion that triggers remedial actions, such as disconnecting customer loads or generators, leading to blackouts, and potentially costly equipment damage. We derive an attack impact model and analyze an optimal attack, consisting of a series of FDIs that minimizes the remaining time until the onset of disruptive remedial actions, leaving the shortest time for the grid to counteract. We show that, based on eavesdropped sensor data and a few feasible-to-obtain system constants, the attacker can learn the attack impact model and achieve the optimal attack in practice. This paper provides essential understanding on the limits of physical impact of the FDIs on power grids, and provides an analysis framework to guide the protection of sensor data links. For countermeasures, we develop efficient algorithms to detect the attack, estimate which sensor data links are under attack, and mitigate attack impact. Our analysis and algorithms are validated by experiments on a physical 16-bus power system test bed and extensive simulations based on a 37-bus power system model.
9 January 2018 in IEEE Transactions on Smart Grid
Recent research has proposed a moving target defense (MTD) approach that actively changes transmission line susceptance to preclude stealthy false data injection (FDI) attacks against the state estimation of a smart grid. However, existing studies were often conducted under a weak adversarial setting, in that they ignore the possibility that alert attackers can also try to detect the activation of MTD before they launch the FDI attacks. We call this new threat as Parameter Confirming-First (PCF) FDI. To improve the stealthiness of MTD, we propose a hidden MTD approach that cannot be detected by the attackers and prove its equivalence to an MTD that maintains the power flows of the whole grid. Moreover, we analyze the completeness of MTD and show that any hidden MTD is incomplete in that FDI attacks may bypass the hidden MTD opportunistically. This result suggests that the stealthiness and completeness are two conflicting goals in MTD design. Finally, we propose an approach to enhancing the hidden MTD against a class of highly structured FDI attacks. We also discuss the MTD’s operational costs under the dc and ac models. We conduct simulations to show the effectiveness of the hidden MTD against PCF-FDI attacks under realistic settings.
6 June 2019 in IEEE Transactions on Smart Grid
Recent cybersecurity incidents such as Stuxnet and Irongate alert us to the threats faced by critical cyber-physical systems. These attacks compromise the control signals to push the system to unsafe regions and meanwhile, inject fake sensor measurements to cover the ongoing attack. Detecting these Stuxnet-like (SL) attacks still remains an open research issue. This paper analyzes the taxonomy, construction, and implication of SL attacks in CPS control loops. We propose to apply the moving target defense (MTD) approach that actively changes the system configuration to detect SL attacks, since these attacks are generally constructed based on the knowledge about the system’s configuration. We analyze the basic conditions for MTD to be successful. Finally, as a case study, we apply MTD for the secondary voltage control of power grids and present simulation results based on the IEEE 39-bus test system under realistic settings.
3 February 2023 in ACM Transactions on Sensor Networks
Current LoRa networks including those following the LoRaWAN specification use the primitive ALOHA mechanism for media access control due to LoRa’s lack of carrier sense capability. From our extensive measurements, the channel activity detection feature that was recently introduced to LoRa for energy-efficiently detecting preamble chirps can also detect payload chirps reliably. This sheds light on an efficient carrier-sense multiple access protocol that we refer to as LMAC for LoRa networks. This article presents the designs of three advancing versions of LMAC that respectively implement carrier-sense multiple access, and balance the communication loads among the channels defined by frequencies and spreading factors based on the end nodes’ local information and then additionally the gateway’s global information. Experiments on a 50-node lab testbed and a 16-node university deployment show that, compared with ALOHA, LMAC brings up to 2.2× goodput improvement and 2.4× reduction of radio energy per successfully delivered frame. Thus, should LoRaWAN’s ALOHA be replaced with LMAC, network performance boosts can be realized.
28 October 2019 in IEEE Transactions on Automatic Control
In this technical note, the trade-off between the attack detectability and the performance degradation in stochastic cyber-physical systems is investigated. We consider a linear time-invariant system in which the attack detector performs a hypothesis test on the state estimation residual of the Kalman filter to detect malicious tampering with the actuator signals. We adopt a notion of attack stealthiness to quantify the degree of stealth by limiting the maximum achievable exponents of both false alarm rate and detection probability below certain thresholds. And conditions for an arbitrary actuator attack to have a specific level of stealthiness are derived. Additionally, we characterize the upper bound of the performance degradation induced by attackers with a given extent of stealthiness and design the attack that achieves the stated upper bound in right-invertible systems. Finally, our results are illustrated via numerical examples.