# Deep Network for Network Intrusion with Concept Drift

01 Jan 2021-pp 933-940

TL;DR: In this paper, a deep learning approach has been proposed for the classification of cluster instances as being intrusive or not intrusive, and a mini-batch Adam optimizer was used due to a large number of hidden layers in the model.

Abstract: A deep learning approach has been proposed for the classification of cluster instances as being intrusive or not intrusive. Mini-batch Adam optimizer was used due to a large number of hidden layers in the model. Massive amounts of data accumulated for training prevented the model from overfitting. After extensive testing of data with various algorithms, it was found that deep learning model with Adam optimizer outperformed others.

##### References

More filters

•

TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

Abstract: Deep neural nets with a large number of parameters are very powerful machine learning systems. However, overfitting is a serious problem in such networks. Large networks are also slow to use, making it difficult to deal with overfitting by combining the predictions of many different large neural nets at test time. Dropout is a technique for addressing this problem. The key idea is to randomly drop units (along with their connections) from the neural network during training. This prevents units from co-adapting too much. During training, dropout samples from an exponential number of different "thinned" networks. At test time, it is easy to approximate the effect of averaging the predictions of all these thinned networks by simply using a single unthinned network that has smaller weights. This significantly reduces overfitting and gives major improvements over other regularization methods. We show that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.

33,597 citations

••

TL;DR: This paper reviews various data mining techniques for anomaly detection to provide better understanding among the existing techniques that may help interested researchers to work future in this direction.

474 citations

••

TL;DR: An overview of each of these challenging areas for learning from, and adapting to, a non-stationary environment that may introduce imbalanced data is presented, followed by a comprehensive review of recent research for developing such a general framework.

Abstract: The primary focus of machine learning has traditionally been on learning from data assumed to be sufficient and representative of the underlying fixed, yet unknown, distribution. Such restrictions on the problem domain paved the way for development of elegant algorithms with theoretically provable performance guarantees. As is often the case, however, real-world problems rarely fit neatly into such restricted models. For instance class distributions are often skewed, resulting in the “class imbalance” problem. Data drawn from non-stationary distributions is also common in real-world applications, resulting in the “concept drift” or “non-stationary learning” problem which is often associated with streaming data scenarios. Recently, these problems have independently experienced increased research attention, however, the combined problem of addressing all of the above mentioned issues has enjoyed relatively little research. If the ultimate goal of intelligent machine learning algorithms is to be able to address a wide spectrum of real-world scenarios, then the need for a general framework for learning from, and adapting to, a non-stationary environment that may introduce imbalanced data can be hardly overstated. In this paper, we first present an overview of each of these challenging areas, followed by a comprehensive review of recent research for developing such a general framework.

256 citations

••

TL;DR: The stochastic runtime of the cross-entropy (CE) algorithm for the well-studied standard problems OneMax and LeadingOnes outperforms theknown runtime bound of the 1-ANT algorithm, a particular ant colony optimization algorithm, and is very close to the known expected runtime of variants of max-min ant systems.

Abstract: This paper analyzes the stochastic runtime of the cross-entropy (CE) algorithm for the well-studied standard problems OneMax and LeadingOnes. We prove that the total number of solutions the algorithm needs to evaluate before reaching the optimal solution (i.e., its runtime) is bounded by a polynomial ${Q(n)}$ in the problem size ${n}$ with a probability growing exponentially to 1 with ${n}$ if the parameters of the algorithm are adapted to ${n}$ in a reasonable way. Our polynomial bound ${Q(n)}$ for OneMax outperforms the well-known runtime bound of the 1-ANT algorithm, a particular ant colony optimization algorithm. Our adaptation of the parameters of the CE algorithm balances the number of iterations needed and the size of the samples drawn in each iteration, resulting in an increased efficiency. For the LeadingOnes problem, we improve the runtime of the algorithm by bounding the sampling probabilities away from 0 and 1. The resulting runtime outperforms the known stochastic runtime for a univariate marginal distribution algorithm, and is very close to the known expected runtime of variants of max-min ant systems. Bounding the sampling probabilities allows the CE algorithm to explore the search space even for test functions with a very rugged landscape as the LeadingOnes function.

26 citations

••

17 May 2009TL;DR: Those working in the field of cyber-based systems, including industrial managers, researchers, engineers, and graduate and senior undergraduate students will find this an indispensable guide in creating systems resistant to and tolerant of cyber attacks.

Abstract: Many networked computer systems are far too vulnerable to cyber attacks that can inhibit their functioning, corrupt important data, or expose private information. Not surprisingly, the field of cyber-based systems is a fertile ground where many tasks can be formulated as learning problems and approached in terms of machine learning algorithms. This book contains original materials by leading researchers in the area and covers applications of different machine learning methods in the reliability, security, performance, and privacy issues of cyber space. It enables readers to discover what types of learning methods are at their disposal, summarizing the state-of-the-practice in this significant area, and giving a classification of existing work. Those working in the field of cyber-based systems, including industrial managers, researchers, engineers, and graduate and senior undergraduate students will find this an indispensable guide in creating systems resistant to and tolerant of cyber attacks.

24 citations