Prakash Ranganathan

As Cyber-Physical Systems (CPS) such as water treatment and distribution systems grow in scale and complexity, their operational technology becomes computationally heterogeneous, spanning from resource-abundant cloud platforms to resource-constrained edge devices. This fundamental diversity challenges the deployment of a single, effective anomaly detection solution, creating a significant architectural dilemma for critical infrastructure operations. Deep learning methods achieve strong anomaly detection capability, but they are often too heavy for resource-constrained edge devices. Although lightweight models can reduce the demand for computing resources, their detection capability also decreases. To address these issues, this paper proposes Transformer-based Anomaly Behavior Analysis for Cyber-Physical Systems (TABA-CPS), a holistic architecture designed to address this conflict through its flexible dual-mode deployment strategy. At its core is a novel Expectation-Maximization Anomaly Transformer (EM-AT) model, an extension of the Anomaly Transformer (AT) that automatically sets the detection threshold, eliminating manual inspection. TABA-CPS offers a flexible, dual-mode deployment strategy: a Performance mode for environments with enough computational resources, which maximizes anomaly detection accuracy and enables Large Language Model (LLM)-based anomaly behavior investigation; and a Computational Resource-constrained Edge (CRCE) mode for resource-constrained devices (e.g., Raspberry Pi), which utilizes model quantization and the ExecuTorch runtime to deliver efficient, low-latency inference. Additionally, the architecture introduces the Green-Water System Anomaly Detection Evaluation (Green-WSADE) framework, inspired by the Green AI idea, to evaluate overall performance on different devices. Experiment results show that Performance mode achieves F₁ scores of 96.32% and 92.47% on Secure Water Treatment (SWaT) and Water Distribution(WADI) datasets, respectively, surpassing leading methods. CRCE mode significantly lowers computational resource consumption, including a 41% reduction in average inference power with only a marginal F₁ score drop (about 0.14% on SWaT, 0.11% on WADI). Moreover, the CRCE mode consistently achieves a computational resource efficiency grade of 1 to 3 across heterogeneous edge devices under the Green-WSADE framework, achieving superior resource efficiency compared to Performance mode on identical resource-constrained hardware. The results demonstrate that TABA-CPS delivers accurate and rapid on-site anomaly detection at the network edge while lowering resource usage, supporting long-term, reliable operation in water treatment and distribution systems.

Microelectronics that make up modern-day devices need to be studied with greater scrutiny on security to mitigate emerging cyber threats. The growth of technology, such as the Internet of Things (IoT), fuels the need to build secure and trustworthy microelectronics that form these end devices. The wide applications of microelectronics broaden the cyber-attack range for adversaries to initiate security attacks. When compromised at a larger scale, impacts can lead to supply and service disruptions in the supply chain, and it must be contained, with risks being eliminated to avoid further impacts. Therefore, understanding the threat surfaces for microelectronics, associated endpoints, evolution, and future developments can help ongoing security research and industrial efforts to protect microelectronics, making them a trustworthy building block of modern electronic devices. This paper reviews the current prevailing security factors contributing to the major impacts of security issues in microelectronics involving hardware and manufacturing vulnerabilities. Furthermore, the exploration extends to various security attacks, including trojans, counterfeiting, and side-channel attacks, covering their attack vectors and associated strategies within the field of microelectronics. This review article also discusses mitigation strategies and security measures for eliminating risks to avoid further impacts. This article provides a comprehensive overview of trustworthy, state-of-the-art microelectronics. By understanding security issues and the current state of countermeasures, we can work towards creating more secure and reliable microelectronic devices across the global supply chain.

Cyanotoxins in freshwater lakes are creating huge economic impacts, prompting state agencies to monitor and predict their formation. Satellite-based remote sensing is often used for early prediction of Harmful Algal Blooms (HABs), but limited literature exists on identifying and generalizing the threshold for toxic bloom formation. Most existing work focused on using a predefined and empirical threshold for spectral indices to identify hotspots of HABs in lakes. However, in this work, a new framework called Cluster Modeling with Explainability for Algal Bloom Prediction (CMEAP) is proposed that uses unsupervised clustering with explainable AI to dynamically determine the cluster boundaries for identifying the HAB regions in lakes. The study attempts to find the thresholds of multiple spectral indices such as Normalized Difference Chlorophyll Index (NDCI), Normalized Difference Vegetation Index (NDVI), Surface Algal Bloom Index (SABI), Algal Bloom Detection index (ABDI), and Adjusted Floating Algae Index (AFAI) for high algal blooms. The spectral indices from four North Dakota lakes were used in the clustering process and validated with ground microcystins concentration across multiple external lakes. The interpretable rule-based explanations for threshold derivation of spectral features for HAB hotspot detection in lakes help to notify the environmental agencies of the areas in lakes where sampling needs to be done. The results suggest that NDCI (0.04-0.35 with a threshold mean of 0.16) plays a major role in cyanoHAB formation in both large and shallow lakes, while NDVI (-0.28) negatively contributes to the formation of cyanoHAB. SABI $\leq$ 0.82 causes a positive impact to high microcystin formation in North Dakota lakes.

Critical infrastructures like the power grid are at risk from increasing cyber threats due to high penetration of interconnected distributed energy resources (DER). Compromised DER endpoints can cause events, data breaches, communication loss, intentional device failures, and even cascading outages. To address these challenges, this paper explores cybersecurity issues in DER management systems (DERMS), including state-of-the-art reviews on architectures, communication protocols, access control privileges, data breaches, identity management policies, attacks such as false data injection, denial of service, distributed denial of service, malware, threats affecting data integrity, and network vulnerabilities. Realistic threat scenarios are outlined, followed by discussions on futuristic solutions like the zero trust framework. The paper presents new architectural patterns for recently released multi-level hierarchical framework as per IEEE 1547.3 standard to handle DERMS data and assets. The paper also discusses potential threats compromising the Confidentiality, Integrity, Availability, and Accountability (CIAA) properties at each level of the IEEE 1547.3 framework. This review is unique and comprehensive, as it covers existing research on cybersecurity challenges in DER-related assets and outlines the necessary capabilities to equip Intrusion Diagnostic Units (IDUs) in future DERMS technologies, all while ensuring compliance with IEEE 1547.3 standard requirements.

This paper investigates the detection of Global Positioning System (GPS) interference during the Dallas Fort Worth (DFW) event from 17 to 19 October 2022, utilizing various machine learning (ML) models. The study examines the effectiveness of several ML models, including neural networks (NN), tree-based models, regression-based models, Bayesian classifiers, distance-based models, and stochastic classifiers, in identifying GPS interference. A simulated training signature was created with 180,000 data points, of which 25,792 were modeled as positive samples indicating GPS interference. Preliminary results reveal that the Multi-Layer Perceptron (MLP) model outperformed others, achieving a 99.8% True Positive Rate (TPR). Additionally, permutation feature importance was utilized to understand how model feature prioritization impacts the detection outcomes. Given the increasing frequency of GPS interference, these findings underscore the critical importance of ML techniques in detecting GPS interference patterns in Automatic Dependent Surveillance-Broadcast (ADS-B) data.

Unmanned aerial systems/vehicles (UAS/UAVs) are widely employed for inspecting high-voltage (HV) Tx lines, characterized by elevated electric (E) and magnetic (H) fields. Operating on batteries, these UAVs are equipped with various electrical sensors, microprocessors, and motors, all susceptible to E/H field effects. This paper explores the distribution of E/H fields in multiple HVTx lines and a microwave tower. Data was collected from one 250 kV _DC , four AC Tx lines (69kV, 230kV, 345kV, and 500kV), and one microwave tower, utilizing DJI UAVs (M2EA, M30, and M300) equipped with onboard setups. Measurements included E field in V/m, H field in mG, Battery voltage in V, Battery current in A, Battery percentage, Battery Temperature in F, latitude, and longitude. Preliminary findings highlight larger E/H field levels within AC Tx lines than DC Tx lines. The paper discusses conditions influencing E/H field strength during UAV operation. Additionally, a proposed multi-staged random forest regressor (RFR) and k-nearest neighbor (KNN) hybrid machine learning (ML) model forecasts UAV battery drain. Results indicate that the hybrid RFR and KNN model yields lower MAPE values compared to standalone models.

Technology has become integral to children’s lives, impacting many aspects, from academic to socialization. Children of today’s generation are growing up with digital devices, such as mobile phones, iPads, computers, video games, and smart gadgets; therefore, screen time has become ubiquitous in children’s daily routines. This paper provides a review of screen time usage and its impact in children across multiple developmental domains: cognitive, language, physical, and socio-emotional domain of children under eight years of age. The cognitive domain considers factors such as attention span and memory; language domain examines vocabulary, speech, and language development; physical domain focuses on motor development, exercise, sleep, and diet; and social-emotional domain considers relationships, self-identity, and emotional behaviors/regulation. Our findings are mixed, as there are both benefits and drawbacks in technology use, but screen time in children requires controlled observation and monitoring for sustainable improved progress across developmental domains. Specific recommendations advise that children’s screen time per day should be limited to zero minutes (min) (0–2 years), <60 min (3–5-years), and 60 min (6–8 years).