With the increased use of automated systems, the Internet of Things (IoT), and sensors for real-time water quality monitoring, there is a greater requirement for the timely detection of unexpected values. Technical faults can introduce anomalies, and a large incoming data rate might make the manual detection of erroneous data difficult. This research introduces and applies a pioneering technology, Multivariate Multiple Convolutional Networks with Long Short-Term Memory (MCN-LSTM), to real-time water quality monitoring. MCN-LSTM is a cutting-edge deep learning technology designed to address the difficulty of detecting anomalies in complicated time series data, particularly in monitoring water quality in a real-world setting. The growing reliance on automated systems, the Internet of Things (IoT), and sensor networks for continuous water quality monitoring is driving the development and deployment of the MCN-LSTM approach. As these technologies become more widely used, the rapid and precise identification of unexpected or aberrant data points becomes critical. Technical difficulties, inherent noise, and a high data influx pose significant hurdles to manual anomaly detection processes. The MCN-LSTM technique takes advantage of deep learning by integrating Multiple Convolutional Networks and Long Short-Term Memory networks. This combination of approaches offers efficient and effective anomaly detection in multivariate time series data, allowing for identifying and flagging unexpected patterns or values that may signal water quality issues. Water quality data anomalies can have far-reaching repercussions, influencing future analyses and leading to incorrect judgments. Anomaly identification must be precise to avoid inaccurate findings and ensure the integrity of water quality tests. Extensive tests were carried out to validate the MCN-LSTM technique utilizing real-world information obtained from sensors installed in water quality monitoring scenarios. The results of these studies proved MCN-LSTM’s outstanding efficacy, with an impressive accuracy rate of 92.3%. This high level of precision demonstrates the technique’s capacity to discriminate between normal and abnormal data instances in real time. The MCN-LSTM technique is a big step forward in water quality monitoring. It can improve decision-making processes and reduce adverse outcomes caused by undetected abnormalities. This unique technique has significant promise for defending human health and maintaining the environment in an era of increased reliance on automated monitoring systems and IoT technology by contributing to the safety and sustainability of water supplies.

In smart power grids, smart meters (SMs) are deployed at the end side of customers to report fine-grained power consumption readings periodically to the utility for energy management and load monitoring. However, electricity theft cyber-attacks can be launched by fraudulent customers through compromising their SMs to report false readings to pay less for their electricity usage. These attacks harmfully affect the power sector since they cause substantial financial loss and degrade the grid performance because the readings are used for energy management. Supervised machine learning approaches have been used in the literature to detect the attacks, but to the best of our knowledge, the use of reinforcement learning (RL) has not been investigated yet. RL can be better than the existing approaches because it can adapt more efficiently with the dynamic nature of cyber-attacks and consumption patters due to its capability to learn by exploration and exploitation mechanisms and deciding optimal actions. In this article, a deep reinforcement learning (DRL) approach is proposed as a promising solution to the electricity theft problem. The samples of real dataset are employed as an environment and rewards are given based on detection errors made during training. In particular, the proposed approach is presented in four different scenarios. First, a global detection model is constructed using a deep Q network (DQN) and a double deep Q network (DDQN) with different architectures of deep neural networks. Second, the global detector is used to build a customized detection model for new customers to achieve high detection accuracy while preventing zero-day attacks. Third, changing the consumption pattern of the existing customers is taken into consideration in the third scenario. Fourth, the challenges of defending against newly launched cyber-attacks are addressed in the fourth scenario. Extensive experiments have been conducted and the results demonstrate that the proposed DRL approach can boost the detection of electricity theft cyberattacks, and it can efficiently learn new consumption patterns, changes in the consumption patterns of existing customers, and newly launched cyber-attacks.

Alzheimer’s disease (AD) is a progressive illness with a slow start that lasts many years; the disease’s consequences are devastating to the patient and the patient’s family. If detected early, the disease’s impact and prognosis can be altered significantly. Blood biosamples are often employed in simple medical testing since they are cost-effective and easy to collect and analyze. This research provides a diagnostic model for Alzheimer’s disease based on federated learning (FL) and hardware acceleration using blood biosamples. We used blood biosample datasets provided by the ADNI website to compare and evaluate the performance of our models. FL has been used to train a shared model without sharing local devices’ raw data with a central server to preserve privacy. We developed a hardware acceleration approach for building our FL model so that we could speed up the training and testing procedures. The VHDL hardware description language and an Altera 10 GX FPGA are utilized to construct the hardware-accelerator approach. The results of the simulations reveal that the proposed methods achieve accuracy and sensitivity for early detection of 89% and 87%, respectively, while simultaneously requiring less time to train than other algorithms considered to be state-of-the-art. The proposed algorithms have a power consumption ranging from 35 to 39 mW, which qualifies them for use in limited devices. Furthermore, the result shows that the proposed method has a lower inference latency (61 ms) than the existing methods with fewer resources.

In the advanced metering infrastructure (AMI) of the smart grid, smart meters (SMs) are deployed to collect fine-grained electricity consumption data, enabling billing, load monitoring, and efficient energy management. However, some consumers engage in fraudulent behavior by hacking their meters, leading to either traditional electricity theft or more sophisticated evasion attacks (EAs). EAs aim to illegally reduce electricity bills while deceiving theft detection mechanisms. The current methods for identifying such attacks raise privacy concerns due to the need for access to consumers’ detailed consumption data to train detection mechanisms. To address privacy concerns, federated learning (FL) is proposed as a collaborative training approach across multiple consumers. Adversarial training (AT) has shown promise in countering evasion threats on machine learning models. This paper, first, investigates the susceptibility of traditional electricity theft classifiers trained by FL to EAs for both independent and identically distributed (IID) and Non-IID consumption data. Then, it investigates the effectiveness of AT in securing the global electricity theft detector against EAs, assuming no misbehavior from the participant consumers in the FL process. After that, we introduce three novel attacks, namely Distillation , No-Adversarial-Sample-Training , and False-Labeling , which can be launched during the AT process to make the global model susceptible to evasion at inference time. Finally, extensive experiments are conducted to validate the severity of these proposed attacks. Our findings reveal that the AT can counter EAs effectively when the FL participants are honest, but it fails when they act maliciously and launch our attacks. This works lays the foundation for future endeavors in exploring additional countermeasures, in conjunction with AT, to bolster the security and resilience of FL machine learning models against adversarial attacks in the context of electricity theft detection.

In smart power grids, electricity theft causes huge economic losses to electrical utility companies. Machine learning (ML), especially deep neural network (DNN) models hold state-of-the-art performance in detecting electricity theft cyberattacks. However, DNN models are vulnerable to adversarial attacks, i.e., evasion attacks. In this work, we, first, study the vulnerability of the DNN-based electricity theft detectors against evasion attacks and the influence of the model’s regularization (generalization) and transferability on robustness. Then, we cluster the power consumers and train a detector for each cluster, and compare the performance and robustness of this detector to a global detector that is trained on all the consumers’ data. The results indicate that the cluster-based detector is not only more robust against evasion attacks but also enhances normal classification accuracy because its training data has more consumption pattern similarity compared to the training data of the global detector which requires higher level of regularization. Then, we develop a cluster-based parallel-ensemble electricity theft detector to achieve high robustness against evasion attacks and high detection accuracy. The proposed detector has two levels of defense, including clustering and ensemble, where clustering decreases regularization and improves robustness, and the ensemble of diverse decision models improves robustness against transferability. We evaluate the detector on different threat models, including Blackbox and Graybox with different knowledge about defense strategy, model architecture, and training dataset. The evaluation results indicate that unlike the existing solutions that sacrifice the normal accuracy of the model to improve the robustness against evasion attacks, the proposed detector outperforms the benchmark defenses in terms of robustness and normal classification accuracy.

Medical image segmentation aims to identify important or suspicious regions within medical images. However, many challenges are usually faced while developing networks for this type of analysis. First, preserving the original image resolution is of utmost importance for this task where identifying subtle features or abnormalities can significantly impact the accuracy of diagnosis. The introduction of the dilated convolution module helped preserve resolution in deep convolutional neural networks, but it has a drawback: loss of local spatial resolution due to increased kernel sparsity in checkboard patterns. To address this, in this work, a double-dilated convolution module is proposed to maintain local spatial resolution while achieving a large receptive field. This approach is applied to tumor segmentation in breast cancer mammograms as a proof-of-concept. Additionally, this study tackles the issue of pixel-level class imbalance in mammogram screenings by comparing various loss functions to find the best one for mass segmentation. Our work also addresses the "black-box" nature of the models by performing quantitative and qualitative evaluations of their interpretability using the Gradient weighted Class Activation Map (Grad-CAM) and comparing it with other explainable models for image segmentation. An experimental analysis on lesion segmentation networks is performed on mammogram screenings from the INBreast dataset, both before and after integrating the proposed dilation module into a state-of-the-art deep convolutional neural network. The results demonstrate the effectiveness of the proposed module in terms of Dice similarity and Miss Detection rate for mass segmentation. Our analysis also promotes using the Tversky Loss function in training pixel-imbalanced data and integrating Grad-CAM for explaining image segmentation results.