Kanti Singh Sangher

Kanti Singh Sangher


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
8 July 2023 in International Journal of System Assurance Engineering and Management
Verified
Journal Article
Closed access
PDF file
KSKanti Singh Sangher
Kanti Singh Sangher
ASArchana Singh
Archana Singh
HPHari Mohan Pandey
Hari Mohan Pandey

18 June 2023 in Information
Verified
Journal Article
Open access
PDF file
KSKanti Singh Sangher
Kanti Singh Sangher
ASArchana Singh
Archana Singh
HPHari Mohan Pandey
Hari Mohan Pandey
Vivek KumarVivek Kumar
Vivek Kumar
The untraceable part of the Deep Web, also known as the Dark Web, is one of the most used “secretive spaces” to execute all sorts of illegal and criminal activities by terrorists, cybercriminals, spies, and offenders. Identifying actions, products, and offenders on the Dark Web is challenging due to its size, intractability, and anonymity. Therefore, it is crucial to intelligently enforce tools and techniques capable of identifying the activities of the Dark Web to assist law enforcement agencies as a support system. Therefore, this study proposes four deep learning architectures (RNN, CNN, LSTM, and Transformer)-based classification models using the pre-trained word embedding representations to identify illicit activities related to cybercrimes on Dark Web forums. We used the Agora dataset derived from the DarkNet market archive, which lists 109 activities by category. The listings in the dataset are vaguely described, and several data points are untagged, which rules out the automatic labeling of category items as target classes. Hence, to overcome this constraint, we applied a meticulously designed human annotation scheme to annotate the data, taking into account all the attributes to infer the context. In this research, we conducted comprehensive evaluations to assess the performance of our proposed approach. Our proposed BERT-based classification model achieved an accuracy score of 96%. Given the unbalancedness of the experimental data, our results indicate the advantage of our tailored data preprocessing strategies and validate our annotation scheme. Thus, in real-world scenarios, our work can be used to analyze Dark Web forums and identify cybercrimes by law enforcement agencies and can pave the path to develop sophisticated systems as per the requirements.


7 April 2023 in Research Square
Verified
Preprint
Open access
PDF file
KSKanti Singh Sangher
Kanti Singh Sangher
ASArchana Singh
Archana Singh
HPHari Mohan Pandey
Hari Mohan Pandey
As Ransomware encrypts user files to prevent access to infected systems its harmful impacts must be quickly identified and remedied. It can be challenging to identify the metrics and parameters to check, especially when using unknown ransomware variants in tests. The proposed work uses machine learning techniques to create a general model that can be used to detect the variations of ransomware families while observing the characteristics of malware. However, early detection is impeded by a dearth of data during the initial phases of an attack, which results in low detection accuracy and a high proportion of false alarms.To overcome these restrictions, our research suggests a revolutionary technique, in machine learning techniques we have proposedRandomClassifier with SMOTE optimizer based on the results received from LazyPredictAutoML and then deep learning algorithm ANN using Root Mean Square Propagation (adam) has been implemented to get the hidden patterns which were not accessible in machine learning approach. Further study focused on improving CNN's performance over RMSProp& Adam, which maintains per-parameter learning rates that are adjusted based on the average of most recent weight gradient magnitudes, using the Adam optimizer. The best option for internet and non-stationary issues is CNN with Adam (e.g. noisy). As gradients grow sparser toward the end of optimization, Adam somewhat surpasses RMSprop. Adam uses CNN and uses the average of the second moments of the gradients (the uncentered variance). The proposed model reported 5.14ms of prediction time and 99.18% accuracy.