With the rapid development of the Artificial Intelligence of Things (AIoT), convolutional neural networks (CNNs) have demonstrated potential and remarkable performance in AIoT applications due to their excellent performance in various inference tasks. However, the users have concerns about privacy leakage for the use of AI and the performance and efficiency of computing on resource-constrained IoT edge devices. Therefore, this paper proposes an efficient privacy-preserving CNN framework (i.e., EPPA) based on the Fully Homomorphic Encryption (FHE) scheme for AIoT application scenarios. In the plaintext domain, we verify schemes with different activation structures to determine the actual activation functions applicable to the corresponding ciphertext domain. Within the encryption domain, we integrate batch normalization (BN) into the convolutional layers to simplify the computation process. For nonlinear activation functions, we use composite polynomials for approximate calculation. Regarding the noise accumulation caused by homomorphic multiplication operations, we realize the refreshment of ciphertext noise through minimal “decryption-encryption” interactions, instead of adopting bootstrapping operations. Additionally, in practical implementation, we convert three-dimensional convolution into two-dimensional convolution to reduce the amount of computation in the encryption domain. Finally, we conduct extensive experiments on four IoT datasets, different CNN architectures, and two platforms with different resource configurations to evaluate the performance of EPPA in detail.

Load frequency control (LFC) is a critical function to balance the power consumption and generation. The grid frequency is a crucial indicator for maintaining balance. However, the widely used information and communication infrastructure for LFC increases the risk of being attacked by malicious actors. The dynamic load altering attack (DLAA) is a typical attack that can destabilize the power system, causing the grid frequency to deviate from its nominal value. Therefore, in this paper, we mathematically analyze the impact of DLAA on the stability of the grid frequency and propose the network parameter regulation (NPR) to mitigate the impact. To begin with, the dynamic LFC model is constructed by highlighting the importance of the network parameter. Then, we model the DLAA and analyze its impact on LFC using the theory of second-order dynamic systems. Finally, we model the NPR and prove its effect in mitigating the DLAA. Besides, we construct a least-effort NPR considering its infrastructure cost and aim to reduce the operation cost. Finally, we carry out extensive simulations to demonstrate the impact of the DLAA and evaluate the mitigation performance of NPR. The proposed cost-benefit NPR approach can not only mitigate the impact of DLAA with 100% and also save 41.18 ＄/MWh in terms of the operation cost.

This paper investigates the detection and mitigation of coordinated cyberattacks on Load Frequency Control (LFC) systems integrated with Battery Energy Storage Systems (BESS). As renewable energy sources gain greater penetration, power grids are becoming increasingly vulnerable to cyber threats, potentially leading to frequency instability and widespread disruptions. We model two significant attack vectors: load-altering attacks (LAAs) and false data injection attacks (FDIAs) that corrupt frequency measurements. These are analyzed for their impact on grid frequency stability in both linear and nonlinear LFC models, incorporating generation rate constraints and nonlinear loads. A coordinated attack strategy is presented, combining LAAs and FDIAs to achieve stealthiness by concealing frequency deviations from system operators, thereby maximizing disruption while evading traditional detection. To counteract these threats, we propose an Unknown Input Observer (UIO)-based detection framework for linear and nonlinear LFCs. The UIO is designed using linear matrix inequalities (LMIs) to estimate system states while isolating unknown attack inputs, enabling attack detection through monitoring measurement residuals against a predefined threshold. For mitigation, we leverage BESS capabilities with two adaptive strategies: dynamic mitigation for dynamic LAAs, which tunes BESS parameters to enhance the system’s stability margin and accelerate convergence to equilibrium; and static mitigation for static LAAs and FDIAs. Simulations show that the UIO achieves high detection accuracy, with residuals exceeding thresholds promptly under coordinated attacks, even in nonlinear models. Mitigation strategies reduce frequency deviations by up to 80% compared to unmitigated cases, restoring stability within seconds.

The load profile is a key characteristic of the power grid and lies at the basis for the power flow control and generation scheduling. However, due to the wide adoption of internet-of-things (IoT)-based metering infrastructure, the cyber vulnerability of load meters has attracted the adversary’s great attention. In this paper, we investigate the vulnerability of manipulating the nodal prices by injecting false load data into the meter measurements. By taking advantage of the changing properties of real-world load profile, we propose a deeply hidden load data attack (i.e., DH-LDA) that can evade bad data detection, clustering-based detection, and price anomaly detection. The main contributions of this work are as follows: (i) We design a stealthy attack framework that exploits historical load patterns to generate load data with minimal statistical deviation from normal measurements, thereby maximizing concealment; (ii) We identify the optimal time window for data injection to ensure that the altered nodal prices follow natural fluctuations, enhancing the undetectability of the attack in real-time market operations; (iii) We develop a resilience evaluation metric and formulate an optimization-based approach to quantify the electricity market’s robustness against DH-LDAs. Our experiments show that the adversary can gain profits from the electricity market while remaining undetected.

In the rapidly evolving urban landscape, outdoor parking lots have become an indispensable part of the city’s transportation system. The growth of parking lots has raised the likelihood of spontaneous vehicle combustion, a significant safety hazard, making smoke detection an essential preventative step. However, the complex environment of outdoor parking lots presents additional challenges for smoke detection, which necessitates the development of more advanced and reliable smoke detection technologies. This paper addresses this concern and presents a novel smoke detection technique designed for the demanding environment of outdoor parking lots. First, we develop a novel dataset to fill the gap, as there is a lack of publicly available data. This dataset encompasses a wide range of smoke and fire scenarios, enhanced with data augmentation to ensure robustness against diverse outdoor conditions. Second, we utilize an optimized YOLOv5s model, integrated with the Squeeze-and-Excitation Network (SENet) attention mechanism, to significantly improve detection accuracy while maintaining real-time processing capabilities. Third, this paper implements an outdoor smoke detection system that is capable of accurately localizing and alerting in real time, enhancing the effectiveness and reliability of emergency response. Experiments show that the system has a high accuracy in terms of detecting smoke incidents in outdoor scenarios.