H e l l o, I'm A r k a!
I am a PhD Information Science and Technology student with a concentration in Cybersecurity from Geroge Mason University.
Research Interests
Publications
Archival
-
Optimizing IDS Rule Placement via Set Covering with Capacity Constraints
-science direct
at Computers & Security, Volume 161, February 2026
Intrusion Detection Systems (IDSs) are essential for identifying and mitigating cyber threats in modern network infrastructures. Although prior work has extensively explored the optimal placement of IDS sensors across networks, optimizing the deployment of detection rules across multiple IDS instances remains a mostly underexplored area. This paper addresses rule deployment by formulating it as a set covering problem with capacity constraints. We seek to minimize the number of rule deployments required to detect potential exploits of all known vulnerabilities while ensuring that no IDS exceeds its inspection capacity. Our model considers the statistical properties of network traffic, enabling the system to account for load surges and reduce the number of packets not inspected by an IDS under high-traffic conditions, such as during Distributed Denial-of-Service attacks. To solve the optimization problem, we introduce a backtracking algorithm enhanced with a priority queue, which efficiently balances rule coverage and capacity constraints. We validate our approach using the CSE-CIC-IDS2017 dataset and a simulated multi-IDS environment. Experimental results demonstrate that our method significantly reduces the number of uninspected packets, while maximizing vulnerability coverage, and outperforms typical rule deployment strategies. This work highlights the critical role of intelligent rule placement in enhancing IDS performance and paves the way for future adaptive and scalable detection systems.Arka Ghosh, Domenico Ditale, Massimiliano Albanese, Preetam Mukherjee
-
Leveraging Artificial Intelligence To Enhance Media Literacy And Combat Misinformation
-SSRN
at JNRID, ISSN:2984-8687, Vol.2, Issue 9, page no.a163-a187, September 2024
This paper explores the integration of Artificial Intelligence (AI) to enhance media literacy and combat misinformation. In the digital age, where misinformation proliferates rapidly across various platforms, it is crucial to equip individuals with the skills to discern credible information from falsehoods. The study investigates AI's role in facilitating media literacy through personalized education, real-time threat detection, and misinformation management. Our findings suggest that AI technologies, such as machine learning and natural language processing, can significantly improve media literacy by providing adaptive learning experiences and automated content verification. This paper emphasizes the potential of AI to not only educate but also protect users from the adverse effects of misinformation, ultimately fostering a more informed and critical society.Srestha Sarkar, Arka Ghosh
-
Improving the Efficiency of Intrusion Detection Systems by Optimizing Rule Deployment Across Multiple IDSs
-scitepress
at the 21st International Conference on Security and Cryptography, SECRYPT 2024
Intrusion Detection Systems (IDS) are strategically installed on specific nodes of an enterprise network to detect ongoing attempts to exploit vulnerable systems. However, deploying a large number of detection rules in each IDS may reduce their efficiency and effectiveness, especially when an IDS is monitoring high-speed data communication channels. Existing research on optimal IDS placement strategies does not address the problem at such a level of granularity. This paper proposes a novel approach for strategic rule deployment subject to various practical constraints. Attack graph-based modeling, along with knowledge of the network topology, is employed to identify the set of suitable rules for deployment on individual IDSs, and capacity constraints are considered to balance the load across IDSs. We provide a formal specification of the optimization problem and propose a practical heuristic solution based on a genetic algorithm.Arka Ghosh, Massimiliano Albanese, Preetam Mukherjee, Amir Alipour-Fanid
-
Ensemble Learning And its Application in Spam Detection. -ieee
at the International Conference on Computer, Electrical & Communication Engineering, ICCECE 2023
An individual model is not always sufficient enough to classify an email. Each spam mail has features that distinguish it from any other regular mail. A model might not always use that feature for classification and thus produce erroneous results. It is essential to cross-verify the output of one model, with that of another model. This can be done using the ensemble learning technique. Previously, this was done using the same model repeatedly, or different variants of the model. However, in this paper, we have used four completely different models and used them to perform max voting, to optimize the result. The models used are Support Vector Machine(SVM), Multinomial Naïve Bayes(MNB), Random Forest(RF), and Decision Tree(DT). After testing all the possible combinations, we were able to conclude that the combination of SVM, MNB, and DT gives the optimal result.Arka Ghosh, Shreyashi Dey, Raja Das, Gautam Mahapatra
Miscellaneous
-
An overview article on 600% increase in Cyber Attack in 2021 -ResearchGate
June,2021
After the pandemic hit the world, there has been an increase in the number of Cyber Attacks by approximately 600% percent. Cyber Security ventures predict cybercrime damages will be around $6 trillion in 2021 up from $3 trillion in 2015. So, is cybersecurity actually implemented properly or are there improvements that are needed to reduce these heavy losses. In this manuscript, we will understand the basics of cybersecurity and the common attacks, the losses they incur, and how they can be prevented.Arka Ghosh
Experience
Cybersecurity Field Training Experience Intern
•Leading a project on attack path construction and design flaw detection using CVEs, aimed at strengthening proactive defense mechanisms in complex systems.
•Conducting field-oriented cybersecurity research under Dr. Massimiliano Albanese, integrating advanced analytical techniques with practical security applications.
•Supervising and mentoring two undergraduate researchers in experimental design and implementation.
Graduate Research Assistant
•Developed an AI-powered tutoring agent for ethics training for an undergraduate course.
•Applied RAG for context-specific feedback by the agent for the students.
Graduate Teaching Assistant
•Assisted in a course that teaches server-side scripting using Node.js with emphasis on secure coding practices.
Research and Development Intern
•Designed and tested Moving Target Defense (MTD) strategies for Software-Defined Networking (SDN), improving resilience against targeted attacks.
Research and Development Intern
•Research and Development work based on Object Detection and Distance Estimation.
Research Intern
•Novel research on topic related to Network Defence under the guidance of Dr. Massimiliano Albanese
Penetration Tester Trainee
•Identified and documented 30+ vulnerabilities in sandbox systems, leading to enhanced mitigation protocols.
Technical Content Writer
• Authored articles on emerging Java technologies, helped increase site traffic by SEO.
Accomplishments
IEEE ComSoc SNTC Student Competition
Gold Award in the international competition where there were participants from all around the world.Award for Outstanding Academic Performance
Awarded by Digital University KeralaCCNA v7.0
Completed the CCNA v7.0 certification from Netcad Academy and Training given by NIIT Foundations.- M1: Introduction to Networks
- M2: Switching, Routing, and Wireless Essentials
- M3: Enterprise Networking, Security, and Automation
Smart India Hackathon, Internal Round
First Runner Up in the SIH 2023 internal hackathon held in DUK.CTF 1.0
First Runner up in CTF held by KSAAC team.Guinness Book of World Record
Participated in a Guinness Book Of World Record Winning Event AI-for India organized by GUVI GEEK and AICTEVarious certifications
I did a lot of certifications during this period including a distance learning cource from IIT Madras on Python Programming. All of the certifications can be found on my Linkdin profile.Education
George Mason University, Fairfax, VA, USA
PhD Information Technology with concentration in CybersecurityCGPA: 4.0/4.0
Digital University Kerala(Formerly IIITM-K), Kerala
M.Sc. Computer Science with Specialization in CybersecurityCGPA: 8.44/10