Prakhyat Kulkarni | PES University (original) (raw)
Uploads
Papers by Prakhyat Kulkarni
Communications in Computer and Information Science, 2020
While online social media is one of the greatest innovations of modern man, it often gets used to... more While online social media is one of the greatest innovations of modern man, it often gets used to perform a barrage of malicious activities which can be anomalous in nature. The area of anomaly detection deals with this challenging task. In this paper, we methodically investigate anomaly detection for the modern content driven attributed graphs. Since labeled graph data is not available for scientific research, we work with a synthetically generated dataset with an unsupervised learning approach to prove that both attribute as well as structure should be considered. We also investigate whether deep learning in this context brings an additional advantage in anomaly detection. We extend the recent work in this area, with an innovative combination of attributed graph embedding with graph convolution technique.
Social media sites connect us to every part of the world and assist in sharing information and en... more Social media sites connect us to every part of the world and assist in sharing information and enable personal and professional growth. All these positives come with their own pitfalls in the form of invasion of privacy, fraud, and identity thefts. This solicits a need for anomaly detection in real time. Since most of the available data sets are unlabelled and unweighted, we extend an unsupervised Oddball technique so that it works on attributed graphs. We demonstrate that considering both the structural aspects and the attributes yield better results by comparing various similarity measures that can be employed on these attributed graphs.
Communications in Computer and Information Science, 2020
While online social media is one of the greatest innovations of modern man, it often gets used to... more While online social media is one of the greatest innovations of modern man, it often gets used to perform a barrage of malicious activities which can be anomalous in nature. The area of anomaly detection deals with this challenging task. In this paper, we methodically investigate anomaly detection for the modern content driven attributed graphs. Since labeled graph data is not available for scientific research, we work with a synthetically generated dataset with an unsupervised learning approach to prove that both attribute as well as structure should be considered. We also investigate whether deep learning in this context brings an additional advantage in anomaly detection. We extend the recent work in this area, with an innovative combination of attributed graph embedding with graph convolution technique.
Social media sites connect us to every part of the world and assist in sharing information and en... more Social media sites connect us to every part of the world and assist in sharing information and enable personal and professional growth. All these positives come with their own pitfalls in the form of invasion of privacy, fraud, and identity thefts. This solicits a need for anomaly detection in real time. Since most of the available data sets are unlabelled and unweighted, we extend an unsupervised Oddball technique so that it works on attributed graphs. We demonstrate that considering both the structural aspects and the attributes yield better results by comparing various similarity measures that can be employed on these attributed graphs.