Periodicals of Engineering and Natural Sciences ISSN 2303-4521 Vol. 8, No. 3, September 2020, pp.1911-1923 1911 Decentralized security and data integrity of blockchain using deep learning techniques Sazeen Taha Abdulrazzaq 1 , Farooq Safauldeen Omar 2 , Maral A. Mustafa 3 1, 2 Kirkuk Technical Collage, Northern Technical University 3 Kirkuk Technical Institute, Northern Technical University ABSTRACT Since the introduction of blockchain, cryptocurrencies have become very attractive as an alternative digital payment method and a highly speculative investment. With the rise in computational power and the growth of available data, the artificial intelligence concept of deep neural networks had a surge of popularity over the last years as well. With the introduction of the long short-term memory (LSTM) architecture, neural networks became more efficient in understanding long-term dependencies in data such as time series. In this research paper, we combine these two topics, by using LSTM networks to make a prognosis of decentralized blockchain security. In particular, we test if LSTM based neural networks can produce profitable trading signals for different blockchains. We experiment with different preprocessing techniques and different targets, both for security regression and trading signal classification. We evaluate LSTM based networks. As data for training we use historical security data in one-minute intervals from August 2019 to August 2020. We measure the performance of the models via back testing, where we simulate trading on historic data not used for training based on the model’s predictions. We anal yze that performance and compare it with the buy and hold strategy. The simulation is carried out on bullish, bearish and stagnating time periods. In the evaluation, we find the best performing target and pinpoint two preprocessing combinations that are most suitable for this task. We conclude that the CNN LSTM hybrid is capable of profitably forecasting trading signals for securing blockchain, outperforming the buy and hold strategy by roughly 30%, while the performance was better. The LTSM method used by current system for encrypting passwords is efficient enough to mitigate modern attacks like man in the middle attack (MITM) and DDOS attack with 95.85% accuracy Keywords: Blockchain, throughput, deep learning, LTSM, security, bitcoin, DDOS, MITM. Corresponding Author: Sazeen Taha Abdulrazzaq Kirkuk Technical Collage, Northern Technical University, Kirkuk, Iraq E-mail: sazeentaha4@ntu.edu.iq 1. Introduction Deep neural networks are a subset of artificial intelligence and their concept is also commonly referred to as deep learning. The core idea behind neural networks was inspired by the brain and has been around for decades. Due to improved learning methods, increasing computational power and large datasets, deep learning has risen in popularity over the last years and is a field of high interest in today’s computer science [1]. Neural networks have had success in solving very complex tasks, long thought to be out of reach for computers, e.g. speech recognition [2], image/video classification, automated translation, text generation, self-driving cars [3] and many more. A very notable accomplishment for neural networks was when the technology company Google introduced a system called Duplex at their developer conference Google I/O in 2018 as mentioned in [4]. Duplex can allegedly make phone calls to book appointments or reservations with no human input necessary, having a natural sounding voice as well as using and understanding nuances of the English language. In the future, many more applications are conceivable and deep learning might replace call centers for providing automated support, assist in elderly care, aid during surgeries and so on. Another IT topic which has been receiving an increasing amount of attention since 2008 is everything related to the blockchain technology [5]. While a blockchain is merely a cryptographically hashed, linked list, it creates possibilities for various applications. One of the many concepts arising from it are decentralized applications and smart contracts [6], agreements that are cryptographically enforced and therefore eliminating the need for notaries, first proposed in [7].