Sunita Vikrant Dhavale’s scientific contributions

Personality of an individual has been a promising variable to understand himself and furthermore the others in the society. It is the logical arrangement of an individual’s attributes like thoughts, feelings, attitudes, behaviour and capability that makes an individual selective. Our personality likewise influences our decisions, medical conditions, assumptions, inclinations and prerequisites. In the scenario of 4G/5G and COVID pandemic, the majority of individuals are dependent on the web gateways as their essential intuitive vehicle for their own and expert necessities; accordingly, it has been a fundamental significance for us to consequently perceive the personality traits of the individual on the opposite side of the screen. Mental analysts have tracked down that an interaction of just 100 ms is adequate to shape judgement about any individual. Thinking about a similar idea towards execution of profound learning for recognition of personality traits, in this work, we propose an intelligent model (iSMART), a combination of depth-wise separable convolution neural network (2D-CNN) and long short-term memory with attention (LSTMwA), that extracts audio and video features through parallel networks and predicts the ultimate personality score of a person. With the top to bottom trial and error, it has been seen that the depth-wise separable CNN reduces the quantity of trainable parameters without compromising the test precision. It is a compelling and lightweight model for recognition of personality traits utilising bi-modular data sources. It likewise accomplishes better accuracy as compared with the outcomes got by the top scoring teams in the ChaLearn Looking at People challenge ECCV 2016. Our proposed model can possibly empower the system with better psychological understandings and improved human–computer interaction.

The current pandemic situation has increased cyber-attacks drastically worldwide. The attackers are using malware like trojans, spyware, rootkits, worms, ransomware heavily. Ransomware is the most notorious malware, yet we did not have any defensive mechanism to prevent or detect a zero-day attack. Most defensive products in the industry rely on either signature-based mechanisms or traffic-based anomalies detection. Therefore, researchers are adopting machine learning and deep learning to develop a behaviour-based mechanism for detecting malware. Though we have some hybrid mechanisms that perform static and dynamic analysis of executable for detection, we have not any full proof detection proof of concept, which can be used to develop a full proof product specific to ransomware. In this work, we have developed a proof of concept for ransomware detection using machine learning models. We have done detailed analysis and compared efficiency between several machine learning models like decision tree, random forest, KNN, SVM, XGBoost and Logistic Regression. We obtained 98.21% accuracy and evaluated various metrics like precision, recall, TP, TN, FP, and FN.

Ransomware is a program used by an attacker or hacker, that locks or encrypts target files or data. The user or the owner of data cannot access these without the explicit assistance of the attacker. After locking or encrypting, the attacker demands ransom generally in the form of cryptocurrencies to permit user to regain access to the locked data. However, there is no guarantee that the user can access seized data again even after that ransom has been paid. Researchers have proposed various tools and techniques to protect and fight against ransomware. Existing tools and methods are not sufficient to detect ransomware early because several new ransomware variants are being introduced every day. Machine learning techniques are used efficiently in various applications like ransomware detection, spam detection, text classification, pattern recognition, etc. Further, deep learning, a subfield of machine learning, eliminates the burden of re-engineering the features for the new types of malware or network attacks that may arise. In this paper, several machine learning-based detection techniques against ransomware are reviewed.

Personality of an individual is the unique way of thinking and behaving in an environment. Automatic assessment of personality has been a challenging problem in the multimedia research due to the subjectivity involved in the assessment. Similarly, the leadership qualities are the set of traits that can influence the group in performing the desired task to achieve the set goal. It can be identified by observing the manifestations of an individual in a test environment. Assessment of leadership qualities using scientific selection techniques have been successfully implemented for selection of military leaders. Our study is intended to explore the feasibility of automatically recognise the leadership qualities and identify its relationship with personality. In this paper, we explored the applicability of existing Deep Learning techniques for recognition of personality traits and proposed the research areas for automated analysis and recognition of leadership qualities.