Ritwik Murali

Dr. Ritwik Murali

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
16 April 2023 in Expert Systems with Applications
Verified
Journal Article
Closed access
RMRitwik Murali
Ritwik Murali
PTPalanisamy T
Palanisamy T
CVC. Shunmuga Velayutham
C. Shunmuga Velayutham

1 August 2019
Verified
Conference Paper
Closed access
HJHariharan Jayakrishnan
Hariharan Jayakrishnan
RMRitwik Murali
Ritwik Murali
Much has been mentioned about the importance of whistleblowing. While all organizations are recommended to have a whistleblowing mechanism, there are very few completely software-based platforms that assist in performing this task securely. The primary concerns are to ensure that the whistleblower remains anonymous and the disclosures are securely delivered to the competent authority, usually media organizations. In this paper, we have analyzed the security of the state of the art software-based whistleblowing platforms and related research, identified security issues and proposed a new architecture that satisfactorily ensures the requirements for anonymous and secure whistleblowing. We have verified the strength of our solution against the existing platforms and related research with the AVISPA (Automated Validation of Internet Security Protocols and Applications) tool. Our approach is practical, backed by cryptographic security and, because of its modularity, can be easily included in the current infrastructure of many whistleblowing platforms. The results show that our architecture is simple, robust and implements a complete end-to-end encryption strategy thus enabling secure and anonymous whistleblowing.

4 December 2024 in IEEE Potentials
Verified
Journal Article
Closed access
RMRitwik Murali
Ritwik Murali
VAVeeramanohar Avudaiappan
Veeramanohar Avudaiappan
In the current academic environment, the increasing prevalence of stress among students has become a critical concern, significantly affecting both mental health and academic outcomes. Factors such as heavy academic workloads, interpersonal conflicts, financial challenges, and societal pressures contribute to cognitive impairments, procrastination, and declining academic performance. Unaddressed, this stress can escalate into severe mental health conditions, including anxiety, depression, and self-harming tendencies, with marginalized or overwhelmed students being particularly vulnerable. Familial expectations, financial instability, imposter syndrome, fear of missing out, cyberbullying, and unsupportive institutional cultures further intensify these challenges. While mental health support mechanisms exist within institutions, they often remain reactive, addressing issues only after they manifest. To address this growing crisis, a shift toward proactive measures is essential, encompassing counseling, meditation, peer support systems, and engagement in extracurricular activities to foster emotional resilience. A holistic and preventative approach that emphasizes early intervention, open communication, and supportive academic environments is imperative to promote students’ well-being and academic success

14 July 2024
Verified
Conference Paper
Open access
RMRitwik Murali
Ritwik Murali
VAVeeramanohar Avudaiappan
Veeramanohar Avudaiappan
Generating 3D objects to produce art that diverges from conventional or existing artistic patterns is a major challenge. Given the growing prevalence of three-dimensional (3D) art in various domains such as architecture, game design, augmented reality, virtual reality, etc., it becomes imperative to devise strategies for generating diverse forms of 3D objects. This research explores the evolution of 3D artistic objects that are complex, aesthetically pleasing and abstract in nature. Eleven different fitness metrics adapted from existing 2D image evolution metrics are first used to generate the 3D models and subsequently 3 new metrics are proposed specifically for the 3D model generation. Then, 4 different methods are used to set the initial population of each of the 14 different metrics resulting in 56 different 3D model evolution techniques. Finally, user feedback (as a survey) is used to evaluate the aesthetics of the different models evolved by these fitness metrics. Results show that the models evolved by the proposed 3D specific fitness metrics were rated higher than others by the users. In a broader context, this research pushes the boundaries of 3D art generation and evaluation techniques, while also providing insights and opportunities for future in-depth exploration of 3D art generation.

9 December 2023
Verified
Conference Paper
Open access
RMRitwik Murali
Ritwik Murali
RSRajkumar Sukumar
Rajkumar Sukumar
MGMary Sanjana Gali
Mary Sanjana Gali
VAVeeramanohar Avudaiappan
Veeramanohar Avudaiappan
Learning one’s first programming language includes challenges of syntax, surplus code and semantics. The learning can be easy or quite hard for a novice programmer depending on the programming language. Even the small “Hello World” program code contains semantic and syntactic complexity. This paper discusses the pros and cons of multiple tools that may be used for syntax independent implementation of solutions. Based on the shortcomings of existing tools, Flowgramming – a platform independent flowcharting software for the novice programmer / problem solver and their instructor, is also proposed in the paper. Flowcharts developed using Flowgramming can be executed by the built-in interpreter which helps the novice programmer focus on understanding the problem solving strategy in a visually appealing manner and also allows for a language independent learning of solution strategies.

15 July 2023
Verified
Conference Paper
Open access
SSSaurav Shyju
Saurav Shyju
RMRitwik Murali
Ritwik Murali
Generative Adversarial Networks (GANs) have gained popularity due to their ability to produce realistic examples from existing data without any supervision. However, they are dependent on their hyperparameters, the tuning of which is usually a manual task. Additionally, the computing resources required for such training are also extremely high. In this paper, ATLAS - a Cloud-based Co-evolutionary Framework for training such adversarial networks using Evolutionary Algorithms is proposed. ATLAS views the GAN components (generator and discriminator) as in a predator-prey relationship and involves co-evolution as a method to address the challenges of overfitting, exploding/vanishing gradients and tunes the hyperparameters of both the components of the GAN. The ATLAS framework is designed to be customizable, and resource flexible to allow for set-up and easy usage for training complex adversarial networks in both distributed and cloud environments. Experiments testing ATLAS capability for anomaly detection were performed and the results show that ATLAS can consistently evolve and produce high-performance GAN models.