Academic literature on the topic 'Microsoft Malware Prediction Competition'

Abstract: Cyber Supply Chain (CSC) system is complex which involves different sub-systems performing various tasks. Security in supply chain is challenging due to the inherent vulnerabilities and threats from any part of the system which can be exploited at any point within the supply chain. This can cause a severe disruption on the overall business continuity. Therefore, it is paramount important to understand and predicate the threats so that organization can undertake necessary control measures for the supply chain security. Cyber Threat Intelligence (CTI) provides an intelligence analysis to discover unknown to known threats using various properties including threat actor skill and motivation, Tactics, Techniques, and Procedure (TT and P), and Indicator of Compromise (IoC). This paper aims to analyse and predicate threats to improve cyber supply chain security. We have applied Cyber Threat Intelligence (CTI) with Machine Learning (ML) techniques to analyse and predict the threats based on the CTI properties. That allows to identify the inherent CSC vulnerabilities so that appropriate control actions can be undertaken for the overall cybersecurity improvement. To demonstrate the applicability of our approach, CTI data is gathered and a number of ML algorithms, i.e., Logistic Regression (LG), Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT), are used to develop predictive analytics using the Microsoft Malware Prediction dataset. Parameters and vulnerabilities and Indicators of compromise (IoC) as output parameters. The results relating to the prediction reveal that Spyware/Ransomware and spear phishing are the most predictable threats in CSC. We have also recommended relevant controls to tackle these threats. We advocate using CTI data for the ML predicate model for the overall CSC cyber security improvement. Keywords: TF-IDF--Term Frequency–Inverse Document Frequency, SVM-Support Vector Machine, CSC-Cyber Supply Chain, CTI-Cyber Threat Intelligence

Abstract As edge computing paradigm achieves great popularity in recent years, there remain some technical challenges that must be addressed to guarantee smart device security in Internet of Things (IoT) environment. Generally, smart devices transmit individual data across the IoT for various purposes nowadays, and it will cause losses and impose a huge threat to users since malware may steal and damage these data. To improve malware detection performance on IoT smart devices, we conduct a malware categorization analysis based on the Kaggle competition of Microsoft Malware Classification Challenge (BIG 2015) dataset in this article. Practically speaking, motivated by temporal convolutional network (TCN) structure, we propose a malware categorization scheme mainly using Word2Vec pre-trained model. Considering that the popular one-hot encoding converts input names from malicious files to high-dimensional vectors since each name is represented as one dimension in one-hot vector space, more compact vectors with fewer dimensions are obtained through the use of Word2Vec pre-training strategy, and then it can lead to fewer parameters and stronger malware feature representation. Moreover, compared with long short-term memory (LSTM), TCN demonstrates better performance with longer effective memory and faster training speed in sequence modeling tasks. The experimental comparisons on this malware dataset reveal better categorization performance with less memory usage and training time. Especially, through the performance comparison between our scheme and the state-of-the-art Word2Vec-based LSTM approach, our scheme shows approximately 1.3% higher predicted accuracy than the latter on this malware categorization task. Additionally, it also demonstrates that our scheme reduces about 90 thousand parameters and more than 1 hour on the model training time in this comparison.

In this era of machinery driven, online social media is a vast growing fact. The main social media is Instagram, Facebook and twitter. These are the media which are connecting the global as fast as other sources. It will be increase as tremendous way in future. These online social media users makes the information independently and also they can gobble the information. There are so many domains accepts the vital role of analyzing the social media. This may improves the throughput and also attain the back-and-forth competition. Now a day the people are spending their most of the time in the online social media. The vast increase in the popularity in the social media also makes the hackers to spam, thus causes the conceivable losses. The Cyber criminals are usually hack by produce the external phishing sites or the malware downloads. This became the major issues in the safety consideration of online social network and this makes the user experience as a damaged one. To combat with the issue of spams, there has been a lot of methods available, Yet, there is not a perfect effective solution for detect the Twitter spams with the exactness. In this paper , the collected tweets are classified with the help of NB and Enhanced Random Forest classifiers. The prediction is then assessed on many validation measures such as accuracy,precision and F1 score.

Основна мета цієї роботи - показати способи підготовки обсягу даних, побудова класифікаційної моделі на величезному наборі даних та оцінка отриманої моделі на тестових даних. Початкова проблема, яка була вирішена в цій роботі, була взята з Microsoft Malware Prediction Competition з сайту Kaggle. Ця проблема відповідає меті, оскільки навчальний набір даних містить різні типи функцій для попередньої обробки та 9 мільйонів рядків.

The main goal of this work is to show the ways of preparation the amount of data, building a classification model on the huge dataset and evaluating resulting model on test data. Initial problem which was solved in this work was taken from Microsoft Malware Prediction Competition from Kaggle site. This task is an appropriate for our goal since training dataset contains different types of features for preprocessing and 9 million of rows.

Over the past decade, malware has grown exponentially. Traditional signature-based approaches to detecting malware have proven their limitations against new malware, and categorizing malware samples has become essential to understanding the basics of malware behavior. Recently, antivirus solutions have increasingly started to adopt machine learning approaches. Unfortunately, there are few open source data sets available for the academic community. One of the largest data sets available was published last year in a competition on Kaggle with data provided by Microsoft for the big data innovators gathering. This chapter explores the problem of malware classification. In particular, this chapter proposes an innovative and scalable approach using convolutional neural networks (CNN) and long short-term memory (LSTM) to assign malware to the corresponding family. The proposed method achieved a classification accuracy of 98.73% and an average log loss of 0.0698 on the validation data.