Vinayakumar R

Simran K, Sriram S, Vinayakumar R et al.

In recent years, the amount of Cyber Security data generated in the form of unstructured texts, for example, social media resources, blogs, articles, and so on has exceptionally increased. Named Entity Recognition (NER) is an initial step towards converting this unstructured data into structured data which can be used by a lot of applications. The existing methods on NER for Cyber Security data are based on rules and linguistic characteristics. A Deep Learning (DL) based approach embedded with Conditional Random Fields (CRFs) is proposed in this paper. Several DL architectures are evaluated to find the most optimal architecture. The combination of Bidirectional Gated Recurrent Unit (Bi-GRU), Convolutional Neural Network (CNN), and CRF performed better compared to various other DL frameworks on a publicly available benchmark dataset. This may be due to the reason that the bidirectional structures preserve the features related to the future and previous words in a sequence.

Simran K, Prathiksha Balakrishna, Vinayakumar R et al.

In recent days, the amount of Cyber Security text data shared via social media resources mainly Twitter has increased. An accurate analysis of this data can help to develop cyber threat situational awareness framework for a cyber threat. This work proposes a deep learning based approach for tweet data analysis. To convert the tweets into numerical representations, various text representations are employed. These features are feed into deep learning architecture for optimal feature extraction as well as classification. Various hyperparameter tuning approaches are used for identifying optimal text representation method as well as optimal network parameters and network structures for deep learning models. For comparative analysis, the classical text representation method with classical machine learning algorithm is employed. From the detailed analysis of experiments, we found that the deep learning architecture with advanced text representation methods performed better than the classical text representation and classical machine learning algorithms. The primary reason for this is that the advanced text representation methods have the capability to learn sequential properties which exist among the textual data and deep learning architectures learns the optimal features along with decreasing the feature size.

Shisrut Rawat, Aishwarya Srinivasan, Vinayakumar R

Security analysts and administrators face a lot of challenges to detect and prevent network intrusions in their organizations, and to prevent network breaches, detecting the breach on time is crucial. Challenges arise while detecting unforeseen attacks. This work includes a performance comparison of classical machine learning approaches that require vast feature engineering, versus integrated unsupervised feature learning and deep neural networks on the NSL-KDD dataset. Various trials of experiments were run to identify suitable hyper-parameters and network configurations of machine learning models. The DNN using 15 features extracted using Principal Component analysis was the most effective modeling method. The further analysis using the Software Defined Networking features also presented a good accuracy using Deep Neural network.

Naveenkumar K S, Vinayakumar R, Soman KP

Text is the major method that is used for communication now a days, each and every day lots of text are created. In this paper the text data is used for the classification of the emotions. Emotions are the way of expression of the persons feelings which has an high influence on the decision making tasks. Datasets are collected which are available publically and combined together based on the three emotions that are considered here positive, negative and neutral. In this paper we have proposed the text representation method TFIDF and keras embedding and then given to the classical machine learning algorithms of which Logistics Regression gives the highest accuracy of about 75.6%, after which it is passed to the deep learning algorithm which is the CNN which gives the state of art accuracy of about 45.25%. For the research purpose the datasets that has been collected are released.

Mohammed Harun Babu R, Vinayakumar R, Soman KP

Recurrent neural network (RNN) is an effective neural network in solving very complex supervised and unsupervised tasks. There has been a significant improvement in RNN field such as natural language processing, speech processing, computer vision and other multiple domains. This paper deals with RNN application on different use cases like Incident Detection, Fraud Detection, and Android Malware Classification. The best performing neural network architecture is chosen by conducting different chain of experiments for different network parameters and structures. The network is run up to 1000 epochs with learning rate set in the range of 0.01 to 0.5.Obviously, RNN performed very well when compared to classical machine learning algorithms. This is mainly possible because RNNs implicitly extracts the underlying features and also identifies the characteristics of the data. This helps to achieve better accuracy.

Vidya Prasad K, Akarsh S, Vinayakumar R et al.

Deep learning mechanisms are prevailing approaches in recent days for the various tasks in natural language processing, speech recognition, image processing and many others. To leverage this we use deep learning based mechanism specifically Bidirectional- Long Short-Term Memory (B-LSTM) for the task of dialectic identification in Arabic and German broadcast speech and Long Short-Term Memory (LSTM) for discriminating between similar Languages. Two unique B-LSTM models are created using the Large-vocabulary Continuous Speech Recognition (LVCSR) based lexical features and a fixed length of 400 per utterance bottleneck features generated by i-vector framework. These models were evaluated on the VarDial 2017 datasets for the tasks Arabic, German dialect identification with dialects of Egyptian, Gulf, Levantine, North African, and MSA for Arabic and Basel, Bern, Lucerne, and Zurich for German. Also for the task of Discriminating between Similar Languages like Bosnian, Croatian and Serbian. The B-LSTM model showed accuracy of 0.246 on lexical features and accuracy of 0.577 bottleneck features of i-Vector framework.

Mohammed Harun Babu R, Vinayakumar R, Soman KP

Deep learning is an advanced model of traditional machine learning. This has the capability to extract optimal feature representation from raw input samples. This has been applied towards various use cases in cyber security such as intrusion detection, malware classification, android malware detection, spam and phishing detection and binary analysis. This paper outlines the survey of all the works related to deep learning based solutions for various cyber security use cases. Keywords: Deep learning, intrusion detection, malware detection, Android malware detection, spam & phishing detection, traffic analysis, binary analysis.

Vinayakumar R, Barathi Ganesh HB, Prabaharan Poornachandran et al.

Deep neural networks (DNNs) have witnessed as a powerful approach in this year by solving long-standing Artificial intelligence (AI) supervised and unsupervised tasks exists in natural language processing, speech processing, computer vision and others. In this paper, we attempt to apply DNNs on three different cyber security use cases: Android malware classification, incident detection and fraud detection. The data set of each use case contains real known benign and malicious activities samples. The efficient network architecture for DNN is chosen by conducting various trails of experiments for network parameters and network structures. The experiments of such chosen efficient configurations of DNNs are run up to 1000 epochs with learning rate set in the range [0.01-0.5]. Experiments of DNN performed well in comparison to the classical machine learning algorithms in all cases of experiments of cyber security use cases. This is due to the fact that DNNs implicitly extract and build better features, identifies the characteristics of the data that lead to better accuracy. The best accuracy obtained by DNN and XGBoost on Android malware classification 0.940 and 0.741, incident detection 1.00 and 0.997 fraud detection 0.972 and 0.916 respectively.

Amara Dinesh Kumar, Vinayakumar R, Soman KP

Hackers and spammers are employing innovative and novel techniques to deceive novice and even knowledgeable internet users. Image spam is one of such technique where the spammer varies and changes some portion of the image such that it is indistinguishable from the original image fooling the users. This paper proposes a deep learning based approach for image spam detection using the convolutional neural networks which uses a dataset with 810 natural images and 928 spam images for classification achieving an accuracy of 91.7% outperforming the existing image processing and machine learning techniques

Amara Dinesh Kumar, Koti Naga Renu Chebrolu, Vinayakumar R et al.

Advanced driver assistance systems are advancing at a rapid pace and all major companies started investing in developing the autonomous vehicles. But the security and reliability is still uncertain and debatable. Imagine that a vehicle is compromised by the attackers and then what they can do. An attacker can control brake, accelerate and even steering which can lead to catastrophic consequences. This paper gives a very short and brief overview of most of the possible attacks on autonomous vehicle software and hardware and their potential implications.

Anu Vazhayil, Vinayakumar R, Soman KP

The knowledge regarding the function of proteins is necessary as it gives a clear picture of biological processes. Nevertheless, there are many protein sequences found and added to the databases but lacks functional annotation. The laboratory experiments take a considerable amount of time for annotation of the sequences. This arises the need to use computational techniques to classify proteins based on their functions. In our work, we have collected the data from Swiss-Prot containing 40433 proteins which is grouped into 30 families. We pass it to recurrent neural network(RNN), long short term memory(LSTM) and gated recurrent unit(GRU) model and compare it by applying trigram with deep neural network and shallow neural network on the same dataset. Through this approach, we could achieve maximum of around 78% accuracy for the classification of protein families.

Vinayakumar R, Barathi Ganesh HB, Anand Kumar M et al.

Health related social media mining is a valuable apparatus for the early recognition of the diverse antagonistic medicinal conditions. Mostly, the existing methods are based on machine learning with knowledge-based learning. This working note presents the Recurrent neural network (RNN) and Long short-term memory (LSTM) based embedding for automatic health text classification in the social media mining. For each task, two systems are built and that classify the tweet at the tweet level. RNN and LSTM are used for extracting features and non-linear activation function at the last layer facilitates to distinguish the tweets of different categories. The experiments are conducted on 2nd Social Media Mining for Health Applications Shared Task at AMIA 2017. The experiment results are considerable; however the proposed method is appropriate for the health text classification. This is primarily due to the reason that, it doesn't rely on any feature engineering mechanisms.