Poushali Sengupta

Poushali Sengupta, Sabita Maharjan, Frank Eliassen et al.

The decentralization of modern energy systems is transforming consumers into prosumers who continuously exchange data with aggregators, peers, and market operators. While such data is essential for peer-to-peer trading, demand response, and distributed forecasting, it can reveal sensitive household patterns and introduce privacy risks. Existing data sharing mechanisms rely on fixed policies or predefined differential privacy budgets, limiting their ability to adapt to variations in reliability, data sensitivity, and request purpose. As a result, prosumers rarely receive explanations for why a request is accepted, rejected, or modified, reducing trust and participation. To address these limitations, we propose X-NegoBox, an explainable negotiation framework for adaptive privacy budgeting and transparent decision making. Each prosumer data is managed locally within a private DataBox, where raw data remain confined. Incoming requests are processed by an Autonomous Privacy Budget Negotiation Protocol (APBNP), which determines an appropriate privacy budget based on trust, feature sensitivity, declared purpose, historical behavior, and risk-aware pricing. When needed, APBNP generates privacy-preserving counter-offers, such as reduced resolution or duration. An Explainable Agreement Layer (X-Contract) produces human- and machine-readable justifications for each decision. After agreement, requester code executes locally in a sandbox, and only sanitized outputs are shared. Experiments on realistic energy market settings show reduced privacy leakage, higher acceptance rates, and improved interpretability.

Poushali Sengupta, Sabita Maharjan, Frank Eliassen et al.

In recent years, explaining decisions made by complex machine learning models has become essential in high-stakes domains such as energy systems, healthcare, finance, and autonomous systems. However, the reliability of these explanations, namely, whether they remain stable and consistent under realistic, non-adversarial changes, remains largely unmeasured. Widely used methods such as SHAP and Integrated Gradients (IG) are well-motivated by axiomatic notions of attribution, yet their explanations can vary substantially even under system-level conditions, including small input perturbations, correlated representations, and minor model updates. Such variability undermines explanation reliability, as reliable explanations should remain consistent across equivalent input representations and small, performance-preserving model changes. We introduce the Explanation Reliability Index (ERI), a family of metrics that quantifies explanation stability under four reliability axioms: robustness to small input perturbations, consistency under feature redundancy, smoothness across model evolution, and resilience to mild distributional shifts. For each axiom, we derive formal guarantees, including Lipschitz-type bounds and temporal stability results. We further propose ERI-T, a dedicated measure of temporal reliability for sequential models, and introduce ERI-Bench, a benchmark designed to systematically stress-test explanation reliability across synthetic and real-world datasets. Experimental results reveal widespread reliability failures in popular explanation methods, showing that explanations can be unstable under realistic deployment conditions. By exposing and quantifying these instabilities, ERI enables principled assessment of explanation reliability and supports more trustworthy explainable AI (XAI) systems.

Poushali Sengupta, Shashi Raj Pandey, Sabita Maharjan et al.

Large language models (LLMs) generate outputs by utilizing extensive context, which often includes redundant information from prompts, retrieved passages, and interaction history. In critical applications, it is vital to identify which context elements actually influence the output, as standard explanation methods struggle with redundancy and overlapping context. Minor changes in input can lead to unpredictable shifts in attribution scores, undermining interpretability and raising concerns about risks like prompt injection. This work addresses the challenge of distinguishing essential context elements from correlated ones. We introduce RISE (Redundancy-Insensitive Scoring of Explanation), a method that quantifies the unique influence of each input relative to others, minimizing the impact of redundancies and providing clearer, stable attributions. Experiments demonstrate that RISE offers more robust explanations than traditional methods, emphasizing the importance of conditional information for trustworthy LLM explanations and monitoring.

Poushali Sengupta, Mayank Raikwar, Sabita Maharjan et al.

Powerful quantum computers in the future may be able to break the security used for communication between vehicles and other devices (Vehicle-to-Everything, or V2X). New security methods called post-quantum cryptography can help protect these systems, but they often require more computing power and can slow down communication, posing a challenge for fast 6G vehicle networks. In this paper, we propose an adaptive post-quantum cryptography (PQC) framework that predicts short-term mobility and channel variations and dynamically selects suitable lattice-, code-, or hash-based PQC configurations using a predictive multi-objective evolutionary algorithm (APMOEA) to meet vehicular latency and security constraints.However, frequent cryptographic reconfiguration in dynamic vehicular environments introduces new attack surfaces during algorithm transitions. A secure monotonic-upgrade protocol prevents downgrade, replay, and desynchronization attacks during transitions. Theoretical results show decision stability under bounded prediction error, latency boundedness under mobility drift, and correctness under small forecast noise. These results demonstrate a practical path toward quantum-safe cryptography in future 6G vehicular networks. Through extensive experiments based on realistic mobility (LuST), weather (ERA5), and NR-V2X channel traces, we show that the proposed framework reduces end-to-end latency by up to 27\%, lowers communication overhead by up to 65\%, and effectively stabilizes cryptographic switching behavior using reinforcement learning. Moreover, under the evaluated adversarial scenarios, the monotonic-upgrade protocol successfully prevents downgrade, replay, and desynchronization attacks.

Poushali Sengupta, Yan Zhang, Frank Eliassen et al.

Explainable AI (XAI) is increasingly essential as modern models become more complex and high-stakes applications demand transparency, trust, and regulatory compliance. Existing global attribution methods often incur high computational costs, lack stability under correlated inputs, and fail to scale efficiently to large or heterogeneous datasets. We address these gaps with \emph{ExCIR} (Explainability through Correlation Impact Ratio), a correlation-aware attribution score equipped with a lightweight transfer protocol that reproduces full-model rankings using only a fraction of the data. ExCIR quantifies sign-aligned co-movement between features and model outputs after \emph{robust centering} (subtracting a robust location estimate, e.g., median or mid-mean, from features and outputs). We further introduce \textsc{BlockCIR}, a \emph{groupwise} extension of ExCIR that scores \emph{sets} of correlated features as a single unit. By aggregating the same signed-co-movement numerators and magnitudes over predefined or data-driven groups, \textsc{BlockCIR} mitigates double-counting in collinear clusters (e.g., synonyms or duplicated sensors) and yields smoother, more stable rankings when strong dependencies are present. Across diverse text, tabular, signal, and image datasets, ExCIR shows trustworthy agreement with established global baselines and the full model, delivers consistent top-$k$ rankings across settings, and reduces runtime via lightweight evaluation on a subset of rows. Overall, ExCIR provides \emph{computationally efficient}, \emph{consistent}, and \emph{scalable} explainability for real-world deployment.

Poushali Sengupta, Sabita Maharjan, frank Eliassen et al.

Location-based vehicular traffic management faces significant challenges in protecting sensitive geographical data while maintaining utility for traffic management and fairness across regions. Existing state-of-the-art solutions often fail to meet the required level of protection against linkage attacks and demographic biases, leading to privacy leakage and inequity in data analysis. In this paper, we propose a novel algorithm designed to address the challenges regarding the balance of privacy, utility, and fairness in location-based vehicular traffic management systems. In this context, utility means providing reliable and meaningful traffic information, while fairness ensures that all regions and individuals are treated equitably in data use and decision-making. Employing differential privacy techniques, we enhance data security by integrating query-based data access with iterative shuffling and calibrated noise injection, ensuring that sensitive geographical data remains protected. We ensure adherence to epsilon-differential privacy standards by implementing the Laplace mechanism. We implemented our algorithm on vehicular location-based data from Norway, demonstrating its ability to maintain data utility for traffic management and urban planning while ensuring fair representation of all geographical areas without being overrepresented or underrepresented. Additionally, we have created a heatmap of Norway based on our model, illustrating the privatized and fair representation of the traffic conditions across various cities. Our algorithm provides privacy in vehicular traffic

Poushali Sengupta, Yan Zhang, Sabita Maharjan et al.

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine learning algorithms, and the research regarding the explainability-accuracy tradeoff is still in its infancy especially when we are concerned about complex machine learning techniques like neural networks and deep learning (DL). In this work, we introduce a new approach for complex models based on the co-relation impact which enhances the explainability considerably while also ensuring the accuracy at a high level. We propose approaches for both scenarios of independent features and dependent features. In addition, we study the uncertainty associated with features and output. Furthermore, we provide an upper bound of the computation complexity of our proposed approach for the dependent features. The complexity bound depends on the order of logarithmic of the number of observations which provides a reliable result considering the higher dimension of dependent feature space with a smaller number of observations.

Poushali Sengupta, Subhankar Mishra

Privacy and Fairness both are very important nowadays. For most of the cases in the online service providing system, users have to share their personal information with the organizations. In return, the clients not only demand a high privacy guarantee to their sensitive data but also expected to be treated fairly irrespective of their age, gender, religion, race, skin color, or other sensitive protected attributes. Our work introduces a novel architecture that is balanced among the privacy-utility-fairness trade-off. The proposed mechanism applies Group Tagging Method and Fairly Iterative Shuffling (FIS) that amplifies privacy through random shuffling and prevents linkage attack. The algorithm introduces a fair classification problem by Relation Impact based on Equalized Minimal FPR-FNR among the protected tagged group. For the count report generation, the aggregator uses TF-IDF to add noise for providing longitudinal Differential Privacy guarantee. Lastly, the mechanism boosts the utility through risk minimization function and obtain the optimal privacy-utility budget of the system. In our work, we have done a case study on gender equality in the admission system and helps to obtain a satisfying result which implies that the proposed architecture achieves the group fairness and optimal privacy-utility trade-off for both the numerical and decision making Queries.

Sudipta Paul, Poushali Sengupta, Subhankar Mishra

Federated learning (FL) is a distributed learning process where the model (weights and checkpoints) is transferred to the devices that posses data rather than the classical way of transferring and aggregating the data centrally. In this way, sensitive data does not leave the user devices. FL uses the FedAvg algorithm, which is trained in the iterative model averaging way, on the non-iid and unbalanced distributed data, without depending on the data quantity. Some issues with the FL are, 1) no scalability, as the model is iteratively trained over all the devices, which amplifies with device drops; 2) security and privacy trade-off of the learning process still not robust enough and 3) overall communication efficiency and the cost are higher. To mitigate these challenges we present Federated Learning and Privately Scaling (FLaPS) architecture, which improves scalability as well as the security and privacy of the system. The devices are grouped into clusters which further gives better privacy scaled turn around time to finish a round of training. Therefore, even if a device gets dropped in the middle of training, the whole process can be started again after a definite amount of time. The data and model both are communicated using differentially private reports with iterative shuffling which provides a better privacy-utility trade-off. We evaluated FLaPS on MNIST, CIFAR10, and TINY-IMAGENET-200 dataset using various CNN models. Experimental results prove FLaPS to be an improved, time and privacy scaled environment having better and comparable after-learning-parameters with respect to the central and FL models.

Poushali Sengupta, Sudipta Paul, Subhankar Mishra

The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage. Differential privacy comes to the rescue with a proper promise of protection against leakage, as it uses a randomized response technique at the time of collection of the data which promises strong privacy with better utility. Differential privacy allows one to access the forest of data by describing their pattern of groups without disclosing any individual trees. The current adaption of differential privacy by leading tech companies and academia encourages authors to explore the topic in detail. The different aspects of differential privacy, it's application in privacy protection and leakage of information, a comparative discussion, on the current research approaches in this field, its utility in the real world as well as the trade-offs - will be discussed.

Poushali Sengupta, Sudipta Paul, Subhankar Mishra

Balancing utility and differential privacy by shuffling or \textit{BUDS} is an approach towards crowd-sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. Here, a novel algorithm is proposed using one-hot encoding and iterative shuffling with the loss estimation and risk minimization techniques, to balance both the utility and privacy. In this work, after collecting one-hot encoded data from different sources and clients, a step of novel attribute shuffling technique using iterative shuffling (based on the query asked by the analyst) and loss estimation with an updation function and risk minimization produces a utility and privacy balanced differential private report. During empirical test of balanced utility and privacy, BUDS produces $ε= 0.02$ which is a very promising result. Our algorithm maintains a privacy bound of $ε= ln [t/((n_1 - 1)^S)]$ and loss bound of $c' \bigg|e^{ln[t/((n_1 - 1)^S)]} - 1\bigg|$.