ARCHIVES

bstract: Several organizations are utilizing cloud technologies and resources to run a spread of applications. These services facilitate businesses save on hardware management, measurability and maintainability concerns of underlying infrastructure. Key cloud service suppliers (CSPs) like Amazon, Microsoft and Google provide Infrastructure as a Service (IaaS) to fulfill the growing demand of such enterprises. This increased utilization of cloud platforms has created it a beautiful target to the attackers, thereby, making the security of cloud services a high priority for CSPs. during this respect, malware has been recognized collectively of the most dangerous and harmful threats to cloud infrastructure (IaaS). during this paper, we tend to study the effectiveness of repeated Neural Networks (RNNs) primarily based deep learning techniques for police work malware in cloud Virtual Machines (VMs). we tend to specialize in 2 major RNN architectures: Long Short Term Memory RNNs (LSTMs) and bidirectional RNNs (BIDIs). These models learn the behavior of malware over time supported run-time fine-grained processes system options like central processor, memory, and disk utilization. we tend to measure our approach on a dataset of 50,480 malicious and benign samples. The method level options were ollected exploitation real malware running in associate degree open on-line cloud surroundings with no restrictions, that is very important to emulate practical cloud supplier settings and additionally capture verity behavior of concealment and complicated malware. Both our LSTM and BIDI models come through high detection rates over ninety nine for various analysis metrics.In addition, associate degree analysis study is conducted to know the importance of input file representations. Our results counsel that especially cases, input ordering will have some have an effect on on the performance of the trained RNN models. Key Words: Deep learning, recurrent neural network, cloud IaaS, online malware detection, long short term memory RNNs, bidirectional RNNs1] B. Grobauer, T. Walloschek, and E. Stocker, “Understanding cloud computing vulnerabilities,” IEEE Security & Privacy, vol. 9, 2011. [2] M. Jensen, J. Schwenk, N. Gruschka, and L. L. Iacono, “On technical security issues in cloud computing,” in IEEE CLOUD, 2009. [3] N. Gruschka and M. Jensen, “Attack surfaces: A taxonomy for attacks on cloud services,” in IEEE CLOUD, 2010, pp. 276–279. [4] Z. Xiao and Y. Xiao, “Security and privacy in cloud computing,” IEEE Communications Surveys & Tutorials, vol. 15, no. 2, 2013. [5] K. Dahbur, B. Mohammad, and A. B. Tarakji, “A survey of risks, threats and vulnerabilities in cloud computing,” in ISWSA, 2011. [6] A. Gholami and E. Laure, “Security and privacy of sensitive data in cloud computing: a survey of recent developments,” arXiv preprint arXiv:1601.01498, 2016. [7] M. Abdelsalam, R. Krishnan, and R. Sandhu, “Clustering-based IaaS cloud monitoring,” in 10th IEEE CLOUD. IEEE, 2017. [8] J. Demme and et al., “On the feasibility of online malware detection with performance counters,” in ACM SIGARCH Computer Architecture News, vol. 41, no. 3. ACM, 2013. [9] G. Tahan, L. Rokach, and Y. Shahar, “Mal-ID: Automatic malware detection using common segment analysis and meta-features,” Journal of Machine Learning Research, vol. 13, no. Apr, 2012. [10] J. Z. Kolter and M. A. Maloof, “Learning to detect and classify malicious executables in the wild,” Journal of Machine Learning Research, vol. 7, no. Dec, 2006. [11] T. Abou-Assaleh and et al., “N-gram-based detection of new malicious code,” in COMPSAC, vol. 2. IEEE, 2004. [12] A. Shabtai and et al., “Detection of malicious code by applying machine learning classifiers on static features: A state-of-the-art survey,” information security technical report, vol. 14, no. 1, 2009. [13] B. Athiwaratkun and J. W. Stokes, “Malware classification with LSTM and GRU language models and a character-level cnn,” in ICASSP. IEEE, 2017. [14] J. Saxe and K. Berlin, “Deep neural network based malware detection using two dimensional binary program features,” in 10th MALWARE. IEEE, 2015. [15] S. Seok and H. Kim, “Visualized malware classification based-on convolutional neural network,” Journal of the Korea Institute of Information Security and Cryptology, vol. 26, no. 1, 2016.