Detecting Malicious Twitter Bots Using Machine Learning
Communications in computer and information science, 2020
Cybercrimes and phishing scams have increased multi-folds over the past few years. Now a days, ha... more Cybercrimes and phishing scams have increased multi-folds over the past few years. Now a days, hackers are coming up with new techniques to hack accounts and gain sensitive information about people and organisations. Social networking site like Twitter is one such tool. And due to its large audience hackers use such sites to reach large number of people. They use such sites to circulate malicious URLs, phishing mails etc. which serve as the entry point into the target system. And with the introduction of Twitter Bots, this work got even easier. Twitter bots can send tweets without any human intervention after a fixed regular interval of time. Also their frequency of tweets is much more than humans and therefore they are frequently used by hackers to spread malicious URLs. And due to large number of active members, these malicious URLs are reaching out to more people, therefore increasing the phishing scams and frauds. So this paper proposes a model which will use different algorithms of machine learning, first to detect twitter bots and then find out which of them is posting malicious URLs. In the proposed model, some features have been suggested which distinguishes a twitter bot account from a benign account. Based on those statistical features, model will be trained. The model will help us to filter out the malicious bots which are harmful for legitimate users.
A Study of Threat Model on Mobile Wallet Based Payment System
EngRN: Computer-Aided Engineering (Topic), 2018
'Digital wallets', gained a lot of popularity in recent times in India and around the glo... more 'Digital wallets', gained a lot of popularity in recent times in India and around the globe. A digital wallet refers to a platform based on electronic device or online service that allows an individual to make electronic transactions. It is a transformed way to pay for things. It is basically paperless payment method which reduces all the hassle of carrying cash with you everywhere. Many digital wallet services have their own mobile apps. Post demonetization in India, the popularity of digital wallet gains exponentially. There are many digital wallets which are currently active in India like Paytm, Freecharge, Jio Money, Airtel Money etc. The aim of this paper is to explore, in detail, about different digital wallets which are very much in use in India and what are their policies and what all measures they take regarding the security of the user data.
Steganography is the study of building systems (stegosystems) that encrypt data in a way, such th... more Steganography is the study of building systems (stegosystems) that encrypt data in a way, such that the datagram created appears to be an innocuous message sent between two endpoints. Steganography aims to provide security by making it difficult for unprivileged endpoints to ascertain that a given message contains any hidden information. Almost all stegosystems, work by embedding the message to be transmitted onto a cover medium and the resulting datagram, which differs from a given innocuous cover by less than a decided threshold value, is then sent over an insecure channel. Most practical stegosystems have thus far used graphic media as a cover channel, but few have used natural language texts (such as English texts) as a cover medium. This paper represents various stegosystems that use natural language as a cover medium and proposes a new approach towards building such a system.
2017 8th International Conference on Information Technology (ICIT)
In this paper a novel data hiding method has been proposed which is based on Non-Linear Feedback ... more In this paper a novel data hiding method has been proposed which is based on Non-Linear Feedback Shift Register and Tinkerbell 2D chaotic map. So far, the major work in Steganography using chaotic map has been confined to image steganography where significant restrictions are there to increase payload. In our work, 2D chaotic map and NLFSR are used to developed a video steganography mechanism where data will be embedded in the segregated frames. This will increase the data hiding limit exponentially. Also, embedding position of each frame will be different from others frames which will increase the overall security of the proposed mechanism. We have achieved this randomized data hiding points by using a chaotic map. Basically, Chaotic theory which is non-linear dynamics physics is using in this era in the field of Cryptography and Steganography and because of this theory, little bit changes in initial condition makes the output totally different. So, it is very hard to get embedding position of data without knowing the initial value of the chaotic map.
Detecting Malicious Twitter Bots Using Machine Learning
Communications in computer and information science, 2020
Cybercrimes and phishing scams have increased multi-folds over the past few years. Now a days, ha... more Cybercrimes and phishing scams have increased multi-folds over the past few years. Now a days, hackers are coming up with new techniques to hack accounts and gain sensitive information about people and organisations. Social networking site like Twitter is one such tool. And due to its large audience hackers use such sites to reach large number of people. They use such sites to circulate malicious URLs, phishing mails etc. which serve as the entry point into the target system. And with the introduction of Twitter Bots, this work got even easier. Twitter bots can send tweets without any human intervention after a fixed regular interval of time. Also their frequency of tweets is much more than humans and therefore they are frequently used by hackers to spread malicious URLs. And due to large number of active members, these malicious URLs are reaching out to more people, therefore increasing the phishing scams and frauds. So this paper proposes a model which will use different algorithms of machine learning, first to detect twitter bots and then find out which of them is posting malicious URLs. In the proposed model, some features have been suggested which distinguishes a twitter bot account from a benign account. Based on those statistical features, model will be trained. The model will help us to filter out the malicious bots which are harmful for legitimate users.
A Study of Threat Model on Mobile Wallet Based Payment System
EngRN: Computer-Aided Engineering (Topic), 2018
'Digital wallets', gained a lot of popularity in recent times in India and around the glo... more 'Digital wallets', gained a lot of popularity in recent times in India and around the globe. A digital wallet refers to a platform based on electronic device or online service that allows an individual to make electronic transactions. It is a transformed way to pay for things. It is basically paperless payment method which reduces all the hassle of carrying cash with you everywhere. Many digital wallet services have their own mobile apps. Post demonetization in India, the popularity of digital wallet gains exponentially. There are many digital wallets which are currently active in India like Paytm, Freecharge, Jio Money, Airtel Money etc. The aim of this paper is to explore, in detail, about different digital wallets which are very much in use in India and what are their policies and what all measures they take regarding the security of the user data.
Steganography is the study of building systems (stegosystems) that encrypt data in a way, such th... more Steganography is the study of building systems (stegosystems) that encrypt data in a way, such that the datagram created appears to be an innocuous message sent between two endpoints. Steganography aims to provide security by making it difficult for unprivileged endpoints to ascertain that a given message contains any hidden information. Almost all stegosystems, work by embedding the message to be transmitted onto a cover medium and the resulting datagram, which differs from a given innocuous cover by less than a decided threshold value, is then sent over an insecure channel. Most practical stegosystems have thus far used graphic media as a cover channel, but few have used natural language texts (such as English texts) as a cover medium. This paper represents various stegosystems that use natural language as a cover medium and proposes a new approach towards building such a system.
2017 8th International Conference on Information Technology (ICIT)
In this paper a novel data hiding method has been proposed which is based on Non-Linear Feedback ... more In this paper a novel data hiding method has been proposed which is based on Non-Linear Feedback Shift Register and Tinkerbell 2D chaotic map. So far, the major work in Steganography using chaotic map has been confined to image steganography where significant restrictions are there to increase payload. In our work, 2D chaotic map and NLFSR are used to developed a video steganography mechanism where data will be embedded in the segregated frames. This will increase the data hiding limit exponentially. Also, embedding position of each frame will be different from others frames which will increase the overall security of the proposed mechanism. We have achieved this randomized data hiding points by using a chaotic map. Basically, Chaotic theory which is non-linear dynamics physics is using in this era in the field of Cryptography and Steganography and because of this theory, little bit changes in initial condition makes the output totally different. So, it is very hard to get embedding position of data without knowing the initial value of the chaotic map.
Uploads
Papers by Nirmalya Kar