ASHA V

Ms. ASHA V

SRM Institute of Science and Technology, Tiruchchirappalli, India
orcid
PhD. Research Scholar Department of Computer Science and Eng...

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2025 in International Journal on Smart Sensing and Intelligent Systems
Verified
Journal Article
Open access
PDF file
ASHA VASHA V
ASHA V
S Kanaga Suba RajaS Kanaga Suba Raja
S Kanaga Suba Raja
The rapid transformation of urban landscapes into intelligent cities, propelled by the Internet of Things (IoT), artificial intelligence (AI), and machine learning (ML), presents substantial opportunities for enhancing urban sustainability, efficiency, and quality of life. However, the interconnected nature of smart urban infrastructures renders them susceptible to significant cybersecurity risks, potentially jeopardizing essential services, and citizen privacy. This study examines the implementation of AI firewalls as a robust solution to strengthen the cybersecurity capabilities of smart cities. Utilizing advanced ML techniques for threat detection, anomaly analysis, and automated responses, AI firewalls can safeguard critical urban infrastructure. A comprehensive review of current literature and emerging AI technologies demonstrates that AI firewalls effectively mitigate cyber threats, protect sensitive data, and ensure the continuity of vital services, thereby fostering public trust and promoting sustainability. The proposed methodology outlines a systematic approach for designing, developing, and implementing AI firewalls, emphasizing scalability, adaptability, and energy efficiency in smart city environments. It also addresses challenges such as cost, privacy concerns, and interoperability through solutions including federated learning, edge computing, and explainable AI (XAI). This research highlights the crucial role of AI firewalls in creating secure, resilient, and sustainable smart cities, facilitating proactive urban governance. Future investigations will focus on enhancing real-time threat response, improving cross-platform integration, and refining privacy-preserving techniques, ensuring AI firewalls remain integral to the evolving landscape of secure urban systems. This study underscores the importance of AI firewalls as a key component of smart city cybersecurity, aligning technological advancements with urban resilience and sustainability objectives.

29 May 2026 in Journal of Internet Services and Information Security
Verified
Journal Article
Closed access
ASHA VASHA V
ASHA V
S Kanaga Suba RajaS Kanaga Suba Raja
S Kanaga Suba Raja
The escalating sophistication of cyber-attacks such as Distributed Denial-of-Service (DDoS) attacks and application-layer threats highlights the shortcomings of traditional, static-signature-based rule-matching systems like Web Application Firewalls (WAFs). Traditional WAF systems are often poor at identifying new attacks, generate numerous false positives, and offer little support for secure auditing and collaborative threat-intelligence sharing. This fig paper presents a cloud-native security framework called WAF-ML-BC, which combines the power of machine-learning-based attack detection with blockchain-based immutable logging. The framework utilizes a stacked ensemble architecture by integrating several machine-learning models via a meta-learning algorithm to enhance attack classification performance. Events are immutably logged using a permissioned blockchain, while federated threat intelligence helps achieve trusted knowledge sharing between different parties involved. The framework was tested on benchmark datasets of web application attack traffic and cyber-security traffic alongside logs of real web traffic. The experimental results showed that the framework achieved a high overall accuracy, precision, recall, and F1-score of 99.1%, 98.7%, 97.8%, and 98.9%, respectively, compared to individual ML models and traditional WAF rules. False positive rates were reduced from 18.3% to 3.1%, leading to more reliable detections. It meets real-time performance by handling web-traffic within the required thresholds at the median, 95th, and 99th percentile at 12, 31, and 47ms respectively. The logging subsystem handled a throughput of nearly 2,840 transactions per second without adversely impacting the traffic processing path. This paper show that by combining ensemble machine learning with blockchain-based auditing, web application security can be significantly improved.

1 January 2022 in International Journal Of Trendy Research In Engineering And Technology
Verified
Journal Article
Closed access
PSP Senthilkumar
P Senthilkumar
ASHA VASHA V
ASHA V
GRG Ramesh
G Ramesh
One of the most pernicious consequences of COVID-19 on society is how it has impacted worldwide mental health, creating new problems and aggravating existing ones. When the few resources are geared for the pandemic, mental health issues and therapy typically take a backseat. Therefore, it's important to monitor any psychological issues before they spiral out of control. The goal of this study is to develop a machine learning-based mental health tracker that primarily focuses on cognitive mental disorders. The MMSE test, which offers a quantifiable measure of cognitive impairment and a way to track cognitive changes over time, is one of the screening methods used to make sure that issues are discovered early. Clusters are created using the K-means clustering algorithm with the potential for dementia incidence.

13 May 2025
Verified
Book Chapter
Closed access
ASHA VASHA V
ASHA V
S Kanaga Suba RajaS Kanaga Suba Raja
S Kanaga Suba Raja
This study introduced an innovative AI-driven solution to enhance the security of home automation systems, addressing the growing vulnerabilities associated with IoT devices. The proposed system combines sophisticated machine-learning techniques with a blockchain-based data-management platform to analyze network-traffic patterns and device behaviors, ensuring data integrity while proactively identifying and combating various cyber threats. Experimental findings demonstrate the system's ability to recognize and mitigate attacks such as denial-of-service and unauthorized access attempts. During a 24-hour evaluation, the AI-powered firewall processed 10,000 requests, successfully blocking 8% of the malicious traffic and identifying suspicious activities for further examination. Notably, it outperformed traditional systems that lacked anomaly-based algorithms by effectively detecting a wide range of significant threats. Future research will focus on enhancing anomaly detection algorithms through user feedback, highlighting the potential of AI-enhanced firewalls to provide robust protection against cyber threats while preserving data confidentiality in emerging 6G networks and smart home ecosystems.

30 June 2026 in Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications
Verified
Journal Article
Closed access
ASHA VASHA V
ASHA V
S Kanaga Suba RajaS Kanaga Suba Raja
S Kanaga Suba Raja
Increasingly, existing cybersecurity infrastructures struggle against complex attacks like Advanced Persistent Threats (APTs), polymorphic malware, encrypted attacks, and zero-day attacks, rendering them ineffective against traditional signature-based and rule-based firewalls. This paper presents a new intelligent AI-based firewall architecture incorporating hybrid deep learning, explainable AI (XAI), federated learning (FL) and multi-agent reinforcement learning (MARL) to enable adaptive and private threat detection on mobile and interactive networks. An end-to-end CNN-LSTM-Autoencoder model was designed and implemented to learn the spatial and temporal characteristics of network traffic, effectively detecting the anomalous traffic patterns indicative of novel attacks. SHAP and LIME techniques were then adopted to produce transparent and interpretable security decisions and federated learning was utilized to enable secure, collaborative sharing of threat intelligence among different organizations without sharing confidential data. Multiple well-known benchmark datasets were used for performance evaluation along with a massive proprietary dataset, SRM-TFC-2024, consisting of 127 million records and spanning the classification and analysis of network flows across various traffic types and attacks, as well as the more established ones, CICIDS2017, UNSW-NB15, NSL-KDD, and CSE-CIC-IDS2018. The experimental results exhibited consistent and high detection rates on all datasets, with classification accuracies between 79% to 82%, precision varying from 87% to 92%, recall from 84% to 90%, F1-score from 85% to 90%, and the false positive rate remained very low between 1% and 3%. The rate of zero-day threat detection was 82% on bothCICIDS2017 and SRM-TFC-2024 datasets, indicating the high potential of the anomaly-based detection method, and the integrated end-to-end system, which consists of the architecture of CNN-LSTM-Autoencoder, federated learning, and Multi-Agent Reinforcement learning, is called QX-FedMARL. Through comparison, the QX-FedMARL firewall works best compared to other rules-based NGFWs. The comparative analysis showed that the QX-FedMARL firewall performs significantly better than the other rule-based NGFW, signature-based IDS, ML-based Firewall, and AI-NGFW architectures with classification precision of 92.0%, recall of 90.0% and the highest F1-score of 91.0% on the tested datasets. These findings suggest that the combined approach of deep learning, explainable AI, federated intelligence and adaptive reinforcement learning presents a robust, scalable, and transparent cybersecurity framework for next-generation intelligent, autonomous firewall systems.

3 August 2026 in Journal of Electronics, Electromedical Engineering, and Medical Informatics
Verified
Journal Article
Open access
PDF file
KAKaliappan A
Kaliappan A
PKP. Senthil Kumar
P. Senthil Kumar
TKTamilselvi K
Tamilselvi K
RTRavi A T
Ravi A T
SPSANTHOSHKUMAR S P
SANTHOSHKUMAR S P
ASHA VASHA V
ASHA V
Wireless Health Monitoring Networks (WHMNs) that utilize Biomedical Electronics (BMEs) are rapidly changing how medical information is gathered and used in contemporary Medical Informatics through providing ongoing, real-time, and remote assessment and monitoring of essential physiological parameters; including electrocardiogram (ECG), body temperature, blood oxygen saturation, and heart rate. A number of constraints can limit the practical implementation of WHMNs including: stringent Quality of Service (QoS) requirements; limited energy availability; network scalability limitations; and significant risks associated with the transfer of sensitive medical information via open wireless networks. While conventional centralized routing and learning based approaches provide the ability to route packets and learn network behavior they require high levels of communication, make the network vulnerable to cyber threats, and do little to protect the privacy of patients' data. This paper describes a QoS aware secure federated intelligence framework designed specifically for BME driven WHMNs. The proposed framework will include: (1) Decentralized Federated Learning to enable distributed intelligence among edge nodes; (2) Trust based QoS Aware Routing to enable reliable and energy efficient communication throughout the network; and (3) a Lightweight Blockchain-Assisted Mechanism to provide authentication, integrity, and tamper resistance to the network. In contrast to traditional federated learning where edge node models are aggregated into a central server model for processing, the proposed framework enables edge nodes to train their own local models on their own data and to share only encrypted model updates rather than raw biomedical data; thereby reducing communication costs and increasing patient data privacy protection. Simulation results show that the proposed framework outperform other state of the art WHMN protocols in terms of Packet Delivery Ratio (PDR); End-To-End Delay (E2ED); Residual Energy per Node (REPN); and Overall Network Lifetime (ONL). Additionally, the security analysis provided in this paper demonstrates the proposed framework's robustness against Insider Attacks, Data Manipulation Attacks, and Unauthorized Access Attacks. These findings indicate the strong feasibility of the proposed framework for next generation Intelligent Healthcare and Medical Informatics Applications.