Searcharxiv⌕ Search

arXiv subjects

Masoud Barati

Publications and source records attributed to Masoud Barati.

At least 19 recordsLinked to original sources
arXiv2026

Runtime Compliance Verification for AI Agents

AI agents now handle personal data through tool use, function calls, and multi turn dialogue, which can create obligations under the General Data Protection Regulation (GDPR). Current testing practices mainly rely on offline red teaming or static prompt review, but they do not guarantee at runtime that agent behavior follows regulatory rules. We propose C-Trace (Compliance Trace based Runtime Agent Conformance Enforcement), a verification framework that: (i) expresses a subset of GDPR requirements, including consent, purpose limitation, data minimization, and the right to erasure, as formal policy predicates over agent execution traces; (ii) uses a runtime monitor that intercepts every tool invocation and model output and rejects non-compliant actions; and (iii) tests the agent with attack dialogues, including DSPy generated prompts and verbatim prompts from red teaming corpora, that try to induce violations. We evaluate the framework on four case studies reframed to GDPR. Under 10 percent per-category extractor noise, including drop-out and over-typing, the monitor keeps the attack success rate at less than or equal to 12 percent, below the baselines we compare against, and false positives at less than or equal to 16 percent, and reaches 0 percent ASR under perfect extraction.

cs.SE↗
arXiv2026

A Privacy by Design Framework for Large Language Model-Based Applications for Children

Children are increasingly using technologies powered by Artificial Intelligence (AI). However, there are growing concerns about privacy risks, particularly for children. Although existing privacy regulations require companies and organizations to implement protections, doing so can be challenging in practice. To address this challenge, this article proposes a framework based on Privacy-by-Design (PbD), which guides designers and developers to take on a proactive and risk-averse approach to technology design. Our framework includes principles from several privacy regulations, such as the General Data Protection Regulation (GDPR) from the European Union, the Personal Information Protection and Electronic Documents Act (PIPEDA) from Canada, and the Children's Online Privacy Protection Act (COPPA) from the United States. We map these principles to various stages of applications that use Large Language Models (LLMs), including data collection, model training, operational monitoring, and ongoing validation. For each stage, we discuss the operational controls found in the recent academic literature to help AI service providers and developers reduce privacy risks while meeting legal standards. In addition, the framework includes design guidelines for children, drawing from the United Nations Convention on the Rights of the Child (UNCRC), the UK's Age-Appropriate Design Code (AADC), and recent academic research. To demonstrate how this framework can be applied in practice, we present a case study of an LLM-based educational tutor for children under 13. Through our analysis and the case study, we show that by using data protection strategies such as technical and organizational controls and making age-appropriate design decisions throughout the LLM life cycle, we can support the development of AI applications for children that provide privacy protections and comply with legal requirements.

cs.AI↗
arXiv2025

DeepKoopFormer: A Koopman Enhanced Transformer Based Architecture for Time Series Forecasting

Time series forecasting plays a vital role across scientific, industrial, and environmental domains, especially when dealing with high-dimensional and nonlinear systems. While Transformer-based models have recently achieved state-of-the-art performance in long-range forecasting, they often suffer from interpretability issues and instability in the presence of noise or dynamical uncertainty. In this work, we propose DeepKoopFormer, a principled forecasting framework that combines the representational power of Transformers with the theoretical rigor of Koopman operator theory. Our model features a modular encoder-propagator-decoder structure, where temporal dynamics are learned via a spectrally constrained, linear Koopman operator in a latent space. We impose structural guarantees-such as bounded spectral radius, Lyapunov based energy regularization, and orthogonal parameterization to ensure stability and interpretability. Comprehensive evaluations are conducted on both synthetic dynamical systems, real-world climate dataset (wind speed and surface pressure), financial time series (cryptocurrency), and electricity generation dataset using the Python package that is prepared for this purpose. Across all experiments, DeepKoopFormer consistently outperforms standard LSTM and baseline Transformer models in terms of accuracy, robustness to noise, and long-term forecasting stability. These results establish DeepKoopFormer as a flexible, interpretable, and robust framework for forecasting in high dimensional and dynamical settings.

cs.LG↗
arXiv2025

A Circular Construction Product Ontology for End-of-Life Decision-Making

Efficient management of end-of-life (EoL) products is critical for advancing circularity in supply chains, particularly within the construction industry where EoL strategies are hindered by heterogenous lifecycle data and data silos. Current tools like Environmental Product Declarations (EPDs) and Digital Product Passports (DPPs) are limited by their dependency on seamless data integration and interoperability which remain significant challenges. To address these, we present the Circular Construction Product Ontology (CCPO), an applied framework designed to overcome semantic and data heterogeneity challenges in EoL decision-making for construction products. CCPO standardises vocabulary and facilitates data integration across supply chain stakeholders enabling lifecycle assessments (LCA) and robust decision-making. By aggregating disparate data into a unified product provenance, CCPO enables automated EoL recommendations through customisable SWRL rules aligned with European standards and stakeholder-specific circularity SLAs, demonstrating its scalability and integration capabilities. The adopted circular product scenario depicts CCPO's application while competency question evaluations show its superior performance in generating accurate EoL suggestions highlighting its potential to greatly improve decision-making in circular supply chains and its applicability in real-world construction environments.

cs.AI↗
arXiv2024

A Global Solution Algorithm for AC Optimal Power Flow through Linear Constrained Quadratic Programming

We formulate the Alternating Current Optimal Power Flow Problem (ACOPF) as a Linear Constrained Quadratic Program (LCQP) with many negative eigenvalues ($r$) and linear constraints, making it NP-hard. We propose two algorithms, Feasible Successive Linear Programming (FSLP) and Feasible Branch-and-Bound (FBB), for a global optimal solution. These use optimization strategies like bounded successive linear programming, convex relaxation, initialization, and branch-and-bound to find a globally optimal solution within a predefined $\epsilon$-tolerance. The complexity of FSLP and FBB is $\mathcal{O}\left(N \prod_{i=1}^r\left\lceil\frac{\sqrt{r}(t_u^i-t_l^i)}{2 \sqrt{\epsilon}}\right\rceil\right)$, where $N$ is the complexity of solving subproblems at each FBB node. Variables $t_l$ and $t_u$ are the lower and upper bounds of $t$, respectively, and $-|t|^2$ is the negative quadratic component in the ACOPF objective function. We use penalized semidefinite modeling, convex relaxation, and line search to design a globally feasible branch-and-bound algorithm for the LCQP form of ACOPF, finding an optimal solution within $\epsilon$-tolerance. Initial results show FSLP and FBB can find global optimal solutions for large-scale ACOPF instances, even with large $r$, and outperform other methods in most PG-lib tests.

math.OC↗
arXiv2024

Enhancing ACPF Analysis: Integrating Newton-Raphson Method with Gradient Descent and Computational Graphs

This paper presents a new method for enhancing Alternating Current Power Flow (ACPF) analysis. The method integrates the Newton-Raphson (NR) method with Enhanced-Gradient Descent (GD) and computational graphs. The integration of renewable energy sources in power systems introduces variability and unpredictability, and this method addresses these challenges. It leverages the robustness of NR for accurate approximations and the flexibility of GD for handling variable conditions, all without requiring Jacobian matrix inversion. Furthermore, computational graphs provide a structured and visual framework that simplifies and systematizes the application of these methods. The goal of this fusion is to overcome the limitations of traditional ACPF methods and improve the resilience, adaptability, and efficiency of modern power grid analyses. We validate the effectiveness of our advanced algorithm through comprehensive testing on established IEEE benchmark systems. Our findings demonstrate that our approach not only speeds up the convergence process but also ensures consistent performance across diverse system states, representing a significant advancement in power flow computation.

math.OC↗
arXiv2024

Synergizing Machine Learning with ACOPF: A Comprehensive Overview

Alternative current optimal power flow (ACOPF) problems have been studied for over fifty years, and yet the development of an optimal algorithm to solve them remains a hot and challenging topic for researchers because of their nonlinear and nonconvex nature. A number of methods based on linearization and convexification have been proposed to solve to ACOPF problems, which result in near-optimal or local solutions, not optimal solutions. Nowadays, with the prevalence of machine learning, some researchers have begun to utilize this technology to solve ACOPF problems using the historical data generated by the grid operators. The present paper reviews the research on solving ACOPF problems using machine learning and neural networks and proposes future studies. This body of research is at the beginning of this area, and further exploration can be undertaken into the possibilities of solving ACOPF problems using machine learning.

math.OC↗
arXiv2023

Harnessing Kernel Regression for Stochastic State Estimation in Solar-Integrated Power Grids

The paper presents a Gaussian/kernel process regression method for real-time state estimation and forecasting of phase angle and angular speed in systems with a high penetration of solar generation units, operating under a sparse measurements regime on both sunny and cloudy days. The method treats unknown terms in the swing equations, such as solar power, as random processes, thereby transforming these equations into stochastic differential equations. The proposed method accurately forecasts and estimates both observed and unobserved operating states, delivering forecasts comparable to those of the standard data-driven Gaussian/kernel process for observed system states. Additionally, the method demonstrates improved accuracy with increased observation frequency and reduced measurement errors in the IEEE 14-bus test system.

eess.SY↗
arXiv2023

XpookyNet: Advancement in Quantum System Analysis through Convolutional Neural Networks for Detection of Entanglement

The application of machine learning models in quantum information theory has surged in recent years, driven by the recognition of entanglement and quantum states, which are the essence of this field. However, most of these studies rely on existing prefabricated models, leading to inadequate accuracy. This work aims to bridge this gap by introducing a custom deep convolutional neural network (CNN) model explicitly tailored to quantum systems. Our proposed CNN model, the so-called XpookyNet, effectively overcomes the challenge of handling complex numbers data inherent to quantum systems and achieves an accuracy of 98.5%. Developing this custom model enhances our ability to analyze and understand quantum states. However, first and foremost, quantum states should be classified more precisely to examine fully and partially entangled states, which is one of the cases we are currently studying. As machine learning and quantum information theory are integrated into quantum systems analysis, various perspectives, and approaches emerge, paving the way for innovative insights and breakthroughs in this field.

quant-ph↗
arXiv2023

Sequence-to-Sequence Forecasting-aided State Estimation for Power Systems

Power system state forecasting has gained more attention in real-time operations recently. Unique challenges to energy systems are emerging with the massive deployment of renewable energy resources. As a result, power system state forecasting are becoming more crucial for monitoring, operating and securing modern power systems. This paper proposes an end-to-end deep learning framework to accurately predict multi-step power system state estimations in real-time. In our model, we employ a sequence-to-sequence framework to allow for multi-step forecasting. Bidirectional gated recurrent units (BiGRUs) are incorporated into the model to achieve high prediction accuracy. The dominant performance of our model is validated using real dataset. Experimental results show the superiority of our model in predictive power compared to existing alternatives.

eess.SY↗
arXiv2023

A New Index based on Power Splitting Indices for Predicting Proper Time of Controlled Islanding

In the event of large disturbances, the practice of controlled islanding is used as a last resort to prevent cascading outages. The application of the strategy at the right time is crucial to maintaining system security. A controlled islanding strategy may be deployed efficiently at the right time by predicting the time of uncontrolled system splitting. The purpose of this study is to predict the appropriate islanding time to prevent catastrophic blackout and uncontrolled islanding based on existing relationships between coherent generator groups. A new instability index is derived from the proximity of inter-area oscillations to power splitting indices. Power splitting indices are derived using synchronization coefficients, which recognize the conditions in the system that warrant controlled islanding. The critical values of indices are calculated in offline mode using simulation data from IEEE 39-Buses, and their online performance is evaluated following a controlled islanding strategy. Through the introduction of these indices, system degradation can be effectively evaluated, and blackouts can be predicted early and prevented by controlled islanding at the right time.

eess.SY↗
arXiv2022

Exploring the Relationships between Privacy by Design Schemes and Privacy Laws: A Comparative Analysis

Internet of Things (IoT) applications have the potential to derive sensitive information about individuals. Therefore, developers must exercise due diligence to make sure that data are managed according to the privacy regulations and data protection laws. However, doing so can be a difficult and challenging task. Recent research has revealed that developers typically face difficulties when complying with regulations. One key reason is that, at times, regulations are vague, and could be challenging to extract and enact such legal requirements. In our research paper, we have conducted a systematic analysis of the data protection laws that are used across different continents, namely: (i) General Data Protection Regulations (GDPR), (ii) the Personal Information Protection and Electronic Documents Act (PIPEDA), (iii) the California Consumer Privacy Act (CCPA), (iv) Australian Privacy Principles (APPs), and (v) New Zealand's Privacy Act 1993. In this technical report, we presented the detailed results of the conducted framework analysis method to attain a comprehensive view of different data protection laws and highlighted the disparities, in order to assist developers in adhering to the regulations across different regions, along with creating a Combined Privacy Law Framework (CPLF). After that, we gave an overview of various Privacy by Design (PbD) schemes developed previously by different researchers. Then, the key principles and individuals' rights of the CPLF were mapped with the privacy principles, strategies, guidelines, and patterns of the Privacy by Design (PbD) schemes in order to investigate the gaps in existing schemes.

cs.CR↗
arXiv2021

A Privacy-Preserving Platform for Recording COVID-19 Vaccine Passports

Digital vaccine passports are one of the main solutions which would allow the restart of travel in a post COVID-19 world. Trust, scalability and security are all key challenges one must overcome in implementing a vaccine passport. Initial approaches attempt to solve this problem by using centralised systems with trusted authorities. However, sharing vaccine passport data between different organisations, regions and countries has become a major challenge. This paper designs a new platform architecture for creating, storing and verifying digital COVID-19 vaccine certifications. The platform makes use of the InterPlanetary File System (IPFS) to guarantee there is no single point of failure and allow data to be securely distributed globally. Blockchain and smart contracts are also integrated into the platform to define policies and log access rights to vaccine passport data while ensuring all actions are audited and verifiably immutable. Our proposed platform realises General Data Protection Regulation (GDPR) requirements in terms of user consent, data encryption, data erasure and accountability obligations. We assess the scalability and performance of the platform using IPFS and Blockchain test networks.

cs.CR↗
arXiv2020

Constraint Clustering Based Islanding Scheme For Power Networks

Controlled islanding, which splits the whole power system into islands, is an effective strategy against rolling blackout during severe disturbances. Finding the islanding solutions in a real-time manner is complicated because of the combinatorial explosion of the solution space occurs for a large power network. In this work, a computationally efficient controlled islanding algorithm is proposed that uses constrained spectral clustering while addressing the generator coherency problem. The objective function used in this controlled islanding algorithm is the minimal power-flow disruption. The sole constraint applied to this solution is related to generator coherency. An undirected edge-weighted graph is created based on absolute values of apparent power flow and constraints related to transmission line availability and coherent generator groups are included by altering the edge weights of the graph and using a subspace projection. Spectral clustering is then applied to the constrained solution subspace to find the islanding solution. The methodology is tested on an IEEE-39 test system with a fully dynamic model. Simulation results demonstrate the efficacy of our approach.

eess.SY↗
arXiv2020

Coherency Detection and Network Partitioning based on Hierarchical DBSCAN

After a sudden disturbance, the energy balance of generators is disturbed, and the power outputs of synchronous generators vary as their rotor angles shift from their equilibrium points. This trend essentially presents the versatile response of each machine to the disturbance. Because of this change, the phase angle of the bus also differs. Hence, the versatile response of each machine can be assessed by the phase angles change at the buses close to the synchronous generator. This paper introduces a new methodology for discovering the degree of coherency among buses using the correlation index of the voltage angle between each pair of buses and use the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to partition the network into islands. The proposed approach also provides the network integrity indices (connectivity, splitting, and separation) for studying the dynamic nature of the power network system. The approach is assessed on an IEEE 39 test system with a fully dynamic model. The simulation results presented in this paper demonstrate the efficiency of the proposed approach.

eess.SP↗
arXiv2019

A Novel Approach in Strategic Planning of Power Networks Against Physical Attacks

The reported work points at developing a practical approach for power transmission planners to secure power networks from potential deliberate attacks. We study the interaction between a system planner (defender) and a rational attacker who threatens the operation of the power grid. In addition to the commonly used hardening strategy for protecting the network, a new sort of resource is introduced under the deception concept. Feint and deception are acknowledged as effective tools for misleading the attacker in strategic planning. To this end, the defender deception is mathematically formulated by releasing misinformation about his plan in the shared cognition-based model. To reduce the risk of damage in case of deception failure, preemptive-goal programming is utilized to prioritize the hardening strategy for the vital components. Furthermore, the value of posturing is introduced which is the benefits that the deception brings to the system. The problems are formulated as tri-level mixed-integer linear programming and solved by the constraint-and-column generation method. Comprehensive simulation studies performed on WSCC 9-bus and IEEE 118-bus systems indicate how the defender will save significant cost from protecting his network with posturing rather than hardening and the proposed approach is a promising development to ensure the secure operation of power networks.

eess.SY↗
arXiv2019

Multi-Layer Spectral Clustering Approach to Intentional Islanding In Bulk Power Systems

Intentional controlled islanding (ICI) is a final resort for preventing a cascading failure and catastrophic power system blackouts. This paper proposes a controlled islanding algorithm that uses spectral clustering over multi-layer graphs to find a suitable islanding solution. The multi-criteria objective function used in this controlled islanding algorithm involves the correlation coefficients between bus frequency components and minimal active and reactive power flow disruption. Similar to the previous studies, the algorithm is applied in two stages. In the first stage, groups of coherent buses are identified with the help of modularity clustering using correlation coefficients between bus frequency components. In the second stage, the ICI solution with minimum active and reactive power flow disruption and satisfying bus coherency is determined by grouping all nodes using spectral clustering on the multi-layer graph. Simulation studies on the IEEE 39-bus test system demonstrate the effectiveness of the method in determining an islanding solution in real time while addressing the generator coherency problem.

eess.SP↗