Biblio

This paper describes the technology of neural network application to solve the problem of information security incidents forecasting. We describe the general problem of analyzing and predicting time series in a graphical and mathematical setting. To solve this problem, it is proposed to use a neural network model. To solve the task of forecasting a time series of information security incidents, data are generated and described on the basis of which the neural network is trained. We offer a neural network structure, train the neural network, estimate it's adequacy and forecasting ability. We show the possibility of effective use of a neural network model as a part of an intelligent forecasting system.

Security is one of the most important needs in network communication. Cryptography is a science which involves two techniques encryption and decryption and it basically enables to send sensitive and confidential data over the unsecure network. The basic idea of cryptography is concealing of the data from unauthenticated users as they can misuse the data. In this paper we use auto associative neural network concept of soft computing in combination with encryption technique to send data securely on communication network.

In recent years, due to the invasion of virus and loopholes, computer networks in colleges and universities have caused great adverse effects on schools, teachers and students. In order to improve the accuracy of computer network security evaluation, Back Propagation (BP) neural network was trained and built. The evaluation index and target expectations have been determined based on the expert system, with 15 secondary evaluation index values taken as input layer parameters, and the computer network security evaluation level values taken as output layer parameter. All data were divided into learning sample sets and forecasting sample sets. The results showed that the designed BP neural network exhibited a fast convergence speed and the system error was 0.000999654. Furthermore, the predictive values of the network were in good agreement with the experimental results, and the correlation coefficient was 0.98723. These results indicated that the network had an excellent training accuracy and generalization ability, which effectively reflected the performance of the system for the computer network security evaluation.

The recent success of brain-inspired deep neural networks (DNNs) in solving complex, high-level visual tasks has led to rising expectations for their potential to match the human visual system. However, DNNs exhibit idiosyncrasies that suggest their visual representation and processing might be substantially different from human vision. One limitation of DNNs is that they are vulnerable to adversarial examples, input images on which subtle, carefully designed noises are added to fool a machine classifier. The robustness of the human visual system against adversarial examples is potentially of great importance as it could uncover a key mechanistic feature that machine vision is yet to incorporate. In this study, we compare the visual representations of white- and black-box adversarial examples in DNNs and humans by leveraging functional magnetic resonance imaging (fMRI). We find a small but significant difference in representation patterns for different (i.e. white- versus black-box) types of adversarial examples for both humans and DNNs. However, human performance on categorical judgment is not degraded by noise regardless of the type unlike DNN. These results suggest that adversarial examples may be differentially represented in the human visual system, but unable to affect the perceptual experience.

Current testing for Deep Neural Networks (DNNs) focuses on quantity of test cases but ignores diversity. To the best of our knowledge, DeepXplore is the first white-box framework for Deep Learning testing by triggering differential behaviors between multiple DNNs and increasing neuron coverage to improve diversity. Since it is based on multiple DNNs facing problems that (1) the framework is not friendly to a single DNN, (2) if incorrect predictions made by all DNNs simultaneously, DeepXplore cannot generate test cases. This paper presents Test4Deep, a white-box testing framework based on a single DNN. Test4Deep avoids mistakes of multiple DNNs by inducing inconsistencies between predicted labels of original inputs and that of generated test inputs. Meanwhile, Test4Deep improves neuron coverage to capture more diversity by attempting to activate more inactivated neurons. The proposed method was evaluated on three popular datasets with nine DNNs. Compared to DeepXplore, Test4Deep produced average 4.59% (maximum 10.49%) more test cases that all found errors and faults of DNNs. These test cases got 19.57% more diversity increment and 25.88% increment of neuron coverage. Test4Deep can further be used to improve the accuracy of DNNs by average up to 5.72% (maximum 7.0%).

Neural Network is used in many applications and guarding its performance against faults is a research challenge. Self-healing neural network is a promising concept for achieving reliability, which is the ability to detect and fix a fault in the system automatically. Most of the current self-healing neural network are based on replication of hardware nodes which causes significant area overhead. The proposed self-healing approach results in a modest area overhead and it is suitable for complex neural network. The proposed method is based on a shared operation and a spare node in each layer which compensates for any faulty node in the layer. Each faulty node will be compensated by its neighbor node, and the neighbor node performs the faulty node as well as its own operations sequentially. In the case the neighbor is faulty, the spare node will compensate for it. The proposed method is implemented using VHDL and the simulation results are obtained using Altira 10 GX FPGA for a different number of nodes. The area overhead is very small for a complex network. The reliability of the proposed method is studied and compared with the traditional neural network.

As the next generation of the power system, smart grid develops towards automated and intellectualized. Along with the benefits brought by smart grids, e.g., improved energy conversion rate, power utilization rate, and power supply quality, are the security challenges. One of the most important issues in smart grids is to ensure reliable communication between the secondary equipment. The state-of-art method to ensure smart grid security is to detect cyber attacks by deep learning. However, due to the small number of negative samples, the performance of the detection system is limited. In this paper, we propose a novel approach that utilizes the Generative Adversarial Network (GAN) to generate abundant negative samples, which helps to improve the performance of the state-of-art detection system. The evaluation results demonstrate that the proposed method can effectively improve the performance of the detection system by 4%.

Recent advances in networking and communication technologies have enabled Internet-of-Things (IoT) devices to communicate more frequently and faster. An IoT device typically transmits data over the Internet which is an insecure channel. Cyber attacks such as denial-of-service (DoS), man-in-middle, and SQL injection are considered as big threats to IoT devices. In this paper, an anomaly-based intrusion detection scheme is proposed that can protect sensitive information and detect novel cyber-attacks. The Artificial Bee Colony (ABC) algorithm is used to train the Random Neural Network (RNN) based system (RNN-ABC). The proposed scheme is trained on NSL-KDD Train+ and tested for unseen data. The experimental results suggest that swarm intelligence and RNN successfully classify novel attacks with an accuracy of 91.65%. Additionally, the performance of the proposed scheme is also compared with a hybrid multilayer perceptron (MLP) based intrusion detection system using sensitivity, mean of mean squared error (MMSE), the standard deviation of MSE (SDMSE), best mean squared error (BMSE) and worst mean squared error (WMSE) parameters. All experimental tests confirm the robustness and high accuracy of the proposed scheme.

Network security became a viral topic nowadays, Anomaly-based Intrusion Detection Systems [1] (IDSs) plays an indispensable role in identifying the attacks from networks and the detection rate and accuracy are said to be high. The proposed work explore this topic and solve this issue by the IDS model developed using Artificial Neural Network (ANN). This model uses Feed - Forward Neural Net algorithms and Probabilistic Neural Network and oppositional based on Particle Swarm optimization Algorithm for lessen the computational overhead and boost the performance level. The whole computing overhead produced in its execution and training are get minimized by the various optimization techniques used in these developed ANN-based IDS system. The experimental study on the developed system tested using the standard NSL-KDD dataset performs well, while compare with other intrusion detection models, built using NN, RB and OPSO algorithms.

False alarm and miss are two general kinds of alarm errors and they can decrease operator's trust in the alarm system. Specifically, there are two different forms of trust in such systems, represented by two kinds of responses to alarms in this research. One is compliance and the other is reliance. Besides false alarm and miss, the two responses are differentially affected by properties of the alarm system, situational factors or operator factors. However, most of the existing studies have qualitatively analyzed the relationship between a single variable and the two responses. In this research, all available experimental studies are identified through database searches using keyword "compliance and reliance" without restriction on year of publication to December 2017. Six relevant studies and fifty-two sets of key data are obtained as the data base of this research. Furthermore, neural network is adopted as a tool to establish the quantitative relationship between multiple factors and the two forms of trust, respectively. The result will be of great significance to further study the influence of human decision making on the overall fault detection rate and the false alarm rate of the human machine system.

At present, the captcha is widely used in the Internet. The method of captcha recognition using the convolutional neural networks was introduced in this paper. It was easier to apply the convolution neural network model of simple training to segment the captcha, and the network structure was established imitating VGGNet model. and the correct rate can be reached more than 90%. For the more difficult segmentation captcha, it can be used the end-to-end thought to the captcha as a whole to training, In this way, the recognition rate of the more difficult segmentation captcha can be reached about 85%.

Accurate model is very important for the control of nonlinear system. The traditional identification method based on shallow BP network is easy to fall into local optimal solution. In this paper, a modeling method for nonlinear system based on improved Deep Belief Network (DBN) is proposed. Continuous Restricted Boltzmann Machine (CRBM) is used as the first layer of the DBN, so that the network can more effectively deal with the actual data collected from the real systems. Then, the unsupervised training and supervised tuning were combine to improve the accuracy of identification. The simulation results show that the proposed method has a higher identification accuracy. Finally, this improved algorithm is applied to identification of diameter model of silicon single crystal and the simulation results prove its excellent ability of parameters identification.

Deep neural networks (DNNs) are effective machine learning models to solve a large class of recognition problems, including the classification of nonlinearly separable patterns. The applications of DNNs are, however, limited by the large size and high energy consumption of the networks. Recently, stochastic computation (SC) has been considered to implement DNNs to reduce the hardware cost. However, it requires a large number of random number generators (RNGs) that lower the energy efficiency of the network. To overcome these limitations, we propose the design of an energy-efficient deep belief network (DBN) based on stochastic computation. An approximate SC activation unit (A-SCAU) is designed to implement different types of activation functions in the neurons. The A-SCAU is immune to signal correlations, so the RNGs can be shared among all neurons in the same layer with no accuracy loss. The area and energy of the proposed design are 5.27% and 3.31% (or 26.55% and 29.89%) of a 32-bit floating-point (or an 8-bit fixed-point) implementation. It is shown that the proposed SC-DBN design achieves a higher classification accuracy compared to the fixed-point implementation. The accuracy is only lower by 0.12% than the floating-point design at a similar computation speed, but with a significantly lower energy consumption.

Intrusion detection systems define an important and dynamic research area for cybersecurity. The role of Intrusion Detection System within security architecture is to improve a security level by identification of all malicious and also suspicious events that could be observed in computer or network system. One of the more specific research areas related to intrusion detection is anomaly detection. Anomaly-based intrusion detection in networks refers to the problem of finding untypical events in the observed network traffic that do not conform to the expected normal patterns. It is assumed that everything that is untypical/anomalous could be dangerous and related to some security events. To detect anomalies many security systems implements a classification or clustering algorithms. However, recent research proved that machine learning models might misclassify adversarial events, e.g. observations which were created by applying intentionally non-random perturbations to the dataset. Such weakness could increase of false negative rate which implies undetected attacks. This fact can lead to one of the most dangerous vulnerabilities of intrusion detection systems. The goal of the research performed was verification of the anomaly detection systems ability to resist this type of attack. This paper presents the preliminary results of tests taken to investigate existence of attack vector, which can use adversarial examples to conceal a real attack from being detected by intrusion detection systems.

This paper proposes a new cryptosystem that combines Diffie-Hellman protocol implemented with hyperelliptic curves over a Galois field GF(2n) with Tree Parity Machine synchronization for a Visible Light Communication indoor channel. The proposed cryptosystem security focuses on overcoming a weakness of neuronal synchronization; specifically, the stimulus vector that is public, which allows an attacker to try to synchronize with one of the participants of the synchronization. Real data receptions of the Visible Light Communication channel are included. In addition, there is an improvement of 115% over a range of 100 $łeq$ tsync$łeq$ 400 of the average synchronization time t\_sync, compared to the classic Tree Parity Machine synchronization.

Transferring artistic styles onto everyday photographs has become an extremely popular task in both academia and industry. Recently, offline training has replaced online iterative optimization, enabling nearly real-time stylization. When those stylization networks are applied directly to high-resolution images, however, the style of localized regions often appears less similar to the desired artistic style. This is because the transfer process fails to capture small, intricate textures and maintain correct texture scales of the artworks. Here we propose a multimodal convolutional neural network that takes into consideration faithful representations of both color and luminance channels, and performs stylization hierarchically with multiple losses of increasing scales. Compared to state-of-the-art networks, our network can also perform style transfer in nearly real-time by performing much more sophisticated training offline. By properly handling style and texture cues at multiple scales using several modalities, we can transfer not just large-scale, obvious style cues but also subtle, exquisite ones. That is, our scheme can generate results that are visually pleasing and more similar to multiple desired artistic styles with color and texture cues at multiple scales.

Stochastic Computing (SC) is an alternative design paradigm particularly useful for applications where cost is critical. SC has been applied to neural networks, as neural networks are known for their high computational complexity. However previous work in this area has critical limitations such as the fully-parallel architecture assumption, which prevent them from being applicable to recent ones such as convolutional neural networks, or ConvNets. This paper presents the first SC architecture for ConvNets, shows its feasibility, with detailed analyses of implementation overheads. Our SC-ConvNet is a hybrid between SC and conventional binary design, which is a marked difference from earlier SC-based neural networks. Though this might seem like a compromise, it is a novel feature driven by the need to support modern ConvNets at scale, which commonly have many, large layers. Our proposed architecture also features hybrid layer composition, which helps achieve very high recognition accuracy. Our detailed evaluation results involving functional simulation and RTL synthesis suggest that SC-ConvNets are indeed competitive with conventional binary designs, even without considering inherent error resilience of SC.

As a problem solving method, neural networks have shown broad applicability from medical applications, speech recognition, and natural language processing. This success has even led to implementation of neural network algorithms into hardware. In this paper, we explore two questions: (a) to what extent microelectronic variations affects the quality of results by neural networks; and (b) if the answer to first question represents an opportunity to optimize the implementation of neural network algorithms. Regarding first question, variations are now increasingly common in aggressive process nodes and typically manifest as an increased frequency of timing errors. Combating variations - due to process and/or operating conditions - usually results in increased guardbands in circuit and architectural design, thus reducing the gains from process technology advances. Given the inherent resilience of neural networks due to adaptation of their learning parameters, one would expect the quality of results produced by neural networks to be relatively insensitive to the rising timing error rates caused by increased variations. On the contrary, using two frequently used neural networks (MLP and CNN), our results show that variations can significantly affect the inference accuracy. This paper outlines our assessment methodology and use of a cross-layer evaluation approach that extracts hardware-level errors from twenty different operating conditions and then inject such errors back to the software layer in an attempt to answer the second question posed above.

Artificial neural networks are complex biologically inspired algorithms made up of highly distributed, adaptive and self-organizing structures that make them suitable for optimization problems. They are made up of a group of interconnected nodes, similar to the great networks of neurons in the human brain. So far, artificial neural networks have not been applied to user modeling in multi-criteria recommender systems. This paper presents neural networks-based user modeling technique that exploits some of the characteristics of biological neurons for improving the accuracy of multi-criteria recommendations. The study was based upon the aggregation function approach that computes the overall rating as a function of the criteria ratings. The proposed technique was evaluated using different evaluation metrics, and the empirical results of the experiments were compared with that of the single rating-based collaborative filtering and two other similarity-based modeling approaches. The two similarity-based techniques used are: the worst-case and the average similarity techniques. The results of the comparative analysis have shown that the proposed technique is more efficient than the two similarity-based techniques and the single rating collaborative filtering technique.

In the paper, we demonstrate a neuromorphic cognitive computing approach for Network Intrusion Detection System (IDS) for cyber security using Deep Learning (DL). The algorithmic power of DL has been merged with fast and extremely power efficient neuromorphic processors for cyber security. In this implementation, the data has been numerical encoded to train with un-supervised deep learning techniques called Auto Encoder (AE) in the training phase. The generated weights of AE are used as initial weights for the supervised training phase using neural networks. The final weights are converted to discrete values using Discrete Vector Factorization (DVF) for generating crossbar weight, synaptic weights, and thresholds for neurons. Finally, the generated crossbar weights, synaptic weights, threshold, and leak values are mapped to crossbars and neurons. In the testing phase, the encoded test samples are converted to spiking form by using hybrid encoding technique. The model has been deployed and tested on the IBM Neurosynaptic Core Simulator (NSCS) and on actual IBM TrueNorth neurosynaptic chip. The experimental results show around 90.12% accuracy for network intrusion detection for cyber security on the physical neuromorphic chip. Furthermore, we have investigated the proposed system not only for detection of malicious packets but also for classifying specific types of attacks and achieved 81.31% recognition accuracy. The neuromorphic implementation provides incredible detection and classification accuracy for network intrusion detection with extremely low power.

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions.

We present a neural network technique for the analysis and extrapolation of time-series data called Neural Decomposition (ND). Units with a sinusoidal activation function are used to perform a Fourier-like decomposition of training samples into a sum of sinusoids, augmented by units with nonperiodic activation functions to capture linear trends and other nonperiodic components. We show how careful weight initialization can be combined with regularization to form a simple model that generalizes well. Our method generalizes effectively on the Mackey-Glass series, a dataset of unemployment rates as reported by the U.S. Department of Labor Statistics, a time-series of monthly international airline passengers, and an unevenly sampled time-series of oxygen isotope measurements from a cave in north India. We find that ND outperforms popular time-series forecasting techniques including LSTM, echo state networks, (S)ARIMA, and SVR with a radial basis function.

Mimicking the collaborative behavior of biological swarms, such as bird flocks and ant colonies, Swarm Intelligence algorithms provide efficient solutions for various optimization problems. On the other hand, a computational model of the human brain, spiking neural networks, has been showing great promise in recognition, inference, and learning, due to recent emergence of neuromorphic hardware for high-efficient and low-power computing. Through bridging these two distinct research fields, we propose a novel computing paradigm that implements the swarm intelligence with a population of coupled spiking neural oscillators in basic leaky integrate-and-fire (LIF) model. Our model behaves as a meta-heuristic searching conducted by multiple collaborative agents. In this design, the oscillating neurons serve as agents in the swarm, search for solutions in frequency coding and communicate with each other through spikes. The firing rate of each agent is adaptive to other agents with better solutions and the optimal solution is rendered as the swarm synchronization is reached. We apply the proposed method to the parameter optimization in several test objective functions and demonstrate its effectiveness and efficiency. Our new computing paradigm expands the computational power of coupled spiking neurons in the field of solving optimization problem and brings opportunities for the connection between individual intelligence and swarm intelligence.