Arivukarasi M
@srmuniv.ac.in
Assistant professor
SRM University
RESEARCH INTERESTS
Networks,machine learning
Scopus Publications
Scopus Publications
A. Manju, A. Revathi, M. Arivukarasi, S. Hariharan, V. Umarani, Shih-Yu Chen, and Jin Wang
Computers, Materials and Continua (Tech Science Press)
M Arivukarasi, A Manju, R Kaladevi, Shanmugasundaram Hariharan, M Mahasree, and Andraju Bhanu Prasad
IEEE
Phishing issues influence the electronic trade in light of the fact that web-based clients trust the Internet climate less. Phishers use procedures that advance to bait online clients, making new phishing sites and spreading messages that attempt to persuade Internet clients to follow deceitful connections to get to their sites. Phishing sites utilize refined procedures that direct internet-based clients to open another page, which has not yet been added to the boycott. A phishing assault that utilizes these new sorts of strategies is known as a zero-day assault. Against phishing techniques can be isolated into specialized or non-specialized arrangements. Nontechnical arrangements used to safeguard the client from phishing assault rely upon utilizing mindfulness and preparing projects to show online customers how to perceive phishing messages and sites. Specialized arrangements, in any case, rely upon building recognition and security models in view of preparing datasets.
A. Manju, M. Arivukarasi, and M. Mahasree
IEEE
In the field of healthcare, computer vision plays a very crucial role which is expected to expand exponentially in the coming decades. Computer vision solely focuses on understanding images and videos. This consists of tasks such as object detection, image classification, and segmentation. The process of visualizing the internal organs of the human body for clinical investigation and medical intrusion is called Medical imaging. Medical imaging has become a tool of paramount importance in clinical trials as it provides a swift diagnosis with visualization and quantitative assessment. Recent breakthroughs have significantly improved image classification and object detection models which are very useful for medical imaging. Medical Imaging technology can assist in detecting even the tiniest aberrations in the human body and for the last decades, computer-supported medical imaging applications have become a trustworthy help for physicians. It not only creates and analyzes images, but also helps doctors with their interpretation. However, a brain-related diagnosis necessitates extreme caution, and even the smallest error in judgment can be disastrous. This research engages with improving the diagnosis accuracy in identifying tumors in the brain. Several imaging technologies like CT scans and X-rays are available for investigating the brain but the MRI (Magnetic Resonance Imaging) has perpetually been the most reliable and safe for such diagnosis. Moreover, it provides a more desirable contrast in information about brain tissues. This further helps in building the model architecture which applies a comprehensive deep learning algorithm and Convolution Neural Networks (CNN) for classifying the tumor's possibility.
M. Arivukarasi and A. Antonidoss
Springer Singapore
M. Arivukarasi and A. Antonidoss
IEEE
In the cutting edge age, all data is effectively open through sites and because of this reason individuals depend totally on online assets. On the in opposition to its focal points, protection and security in online media are the primary concern overall as a result of the ascent in phishing assaults propelled on the web. The quantity of phishing sites expands each month focusing on in excess of 450 brands, according to the reports distributed by against phishing working groups. Generally boycotts are utilized to distinguish the URL assaults. In any case, with the exponential increment in the quantity of phishing sites, this strategy has its own restrictions and it additionally neglects to identify recently created phishing URLs which can be unraveled utilizing AI or profound learning strategies. Here we present a near report between established AI procedure calculated relapse utilizing bigram, profound learning strategies like convolution neural network and Recurrent Neural Network long present moment memory as models used to identify noxious Uniform Resource Locators. On correlation Recurrent neural network and long short term memory gave the best exactness of about 98% for the grouping of phishing Uniform Resources.
The objective of this undertaking is to apply neural systems to phishing email recognition and assess the adequacy of this methodology. We structure the list of capabilities, process the phishing dataset, and execute the Neural Network frameworks. we analyze its exhibition against that of other real Artificial Intelligence Techniques – DT , K-nearest , NB and SVM machine.. The equivalent dataset and list of capabilities are utilized in the correlation. From the factual examination, we infer that Neural Networks with a proper number of concealed units can accomplish acceptable precision notwithstanding when the preparation models are rare. Additionally, our element determination is compelling in catching the qualities of phishing messages, as most AI calculations can yield sensible outcomes with it.
Phishing over web is a saturating risk that speaks to fifth of online business sites. Regardless of the broad research in phishing sites location, none adapt with the nonstop improvement in phishing methods. Along these lines, a subjective, dynamic, and self-versatile phishing location framework is expected to consequently distinguish new phishing methodologies. Subjective Computing methods emulate the thinking and learning capacities of human mind. In this paper, we propose a psychological structure for phishing sites recognition. The structure utilizes an intellectual system called a bidirectional long momentary memory (BLSTM) intermittent neural system (RNN). Moreover, we incorporated a Convolutional Neural Network (CNN) for semantically distinguishing items and activities in sites' pictures. Existing phishing site discovery frameworks experience the ill effects of poor picture highlights execution as they utilize just factual and basic highlights of pictures. The system should outflank existing frameworks since it can gain from setting persistently identify new phishing strategies