Biblio

This paper proposes a new two-stage encryption method to increase the cryptographic strength of the AES algorithm, which is based on stochastic error of a neural network. The composite encryption key in AES neural network cryptosystem are the weight matrices of synaptic connections between neurons and the metadata about the architecture of the neural network. The stochastic nature of the prediction error of the neural network provides an ever-changing pair key-ciphertext. Different topologies of the neural networks and the use of various activation functions increase the number of variations of the AES neural network decryption algorithm. The ciphertext is created by the forward propagation process. The encryption result is reversed back to plaintext by the reverse neural network functional operator.

Robustness verification of neural networks (NNs) is a challenging and significant problem, which draws great attention in recent years. Existing researches have shown that bound propagation is a scalable and effective method for robustness verification, and it can be implemented on GPUs and TPUs to get parallelized. However, the bound propagation methods naturally produce weak bound due to linear relaxations on the neurons, which may cause failure in verification. Although tightening techniques for simple ReLU networks have been explored, they are not applicable for NNs with general activation functions such as Sigmoid and Tanh. Improving robustness verification on these NNs is still challenging. In this paper, we propose a Branch-and-Bound (BaB) style method to address this problem. The proposed BaB procedure improves the weak bound by splitting the input domain of neurons into sub-domains and solving the corresponding sub-problems. We propose a generic heuristic function to determine the priority of neuron splitting by scoring the relaxation and impact of neurons. Moreover, we combine bound optimization with the BaB procedure to improve the weak bound. Experimental results demonstrate that the proposed method gains up to 35% improvement compared to the state-of-art CROWN method on Sigmoid and Tanh networks.

The wide application of deep learning techniques is boosting the regulation of deep learning models, especially deep neural networks (DNN), as commercial products. A necessary prerequisite for such regulations is identifying the owner of deep neural networks, which is usually done through the watermark. Current DNN watermarking schemes, particularly white-box ones, are uniformly fragile against a family of functionality equivalence attacks, especially the neuron permutation. This operation can effortlessly invalidate the ownership proof and escape copyright regulations. To enhance the robustness of white-box DNN watermarking schemes, this paper presents a procedure that aligns neurons into the same order as when the watermark is embedded, so the watermark can be correctly recognized. This neuron alignment process significantly facilitates the functionality of established deep neural network watermarking schemes.

Transformer is the key equipment of power system, and its stable operation is very important to the security of power system In practical application, with the progress of technology, the performance of transformer becomes more and more important, but faults also occur from time to time in practical application, and the traditional manual fault diagnosis needs to consume a lot of time and energy. At present, the rapid development of artificial intelligence technology provides a new research direction for timely and accurate detection and treatment of transformer faults. In this paper, a method of transformer fault diagnosis using artificial neural network is proposed. The neural network algorithm is used for off-line learning and training of the operation state data of normal and fault states. By adjusting the relationship between neuron nodes, the mapping relationship between fault characteristics and fault location is established by using network layer learning, Finally, the reasoning process from fault feature to fault location is realized to realize intelligent fault diagnosis.

The error-resiliency of Artificial Intelligence (AI) hardware accelerators is a major concern, especially when they are deployed in mission-critical and safety-critical applications. In this paper, we propose a neuron fault tolerance strategy for Spiking Neural Networks (SNNs). It is optimized for low area and power overhead by leveraging observations made from a large-scale fault injection experiment that pinpoints the critical fault types and locations. We describe the fault modeling approach, the fault injection framework, the results of the fault injection experiment, the fault-tolerance strategy, and the fault-tolerant SNN architecture. The idea is demonstrated on two SNNs that we designed for two SNN-oriented datasets, namely the N-MNIST and IBM's DVS128 gesture datasets.

Experimental implementation of phase-locked loop (PLL) with bandpass filter is proposed. Such PLL is noteworthy for neuron-like dynamics. It generates both regular and chaotic spikes and bursts. Previously proposed hardware implementation of this system has significant disadvantage – absence of excitable (non-oscillating) mode that is vital for brain neurons. The proposed electronic neuron-like generator is modified and could be used for hardware implementation of spiking neural networks.

This paper discusses DDoS attacks, their current threat level and IDS systems, which are one of the main tools to protect against them. It focuses on the problems encountered by IDS systems in detecting DDoS attacks and the difficulties and challenges of integrating them with artificial intelligence systems today.

In this paper, a multiple switches open-fault diagnostic method using ANNs (Artificial Neural Networks) for three-phase PWM (Pulse Width Modulation) converters is proposed. When an open-fault occurs on switches in the converter, the stator currents can include dc and harmonic components. Since these abnormal currents cannot be easily cut off by protection circuits, secondary faults can occur in peripherals. Therefore, a method of diagnosing the open-fault is required. For open-faults for single switch and double switches, there are 21 types of fault modes depending on faulty switches. In this paper, these fault modes are localized by using the dc component and THD (Total Harmonics Distortion) in fault currents. For obtaining the dc component and THD in the currents, an ADALINE (Adaptive Linear Neuron) is used. For localizing fault modes, two ANNs are used in series; the 21 fault modes are categorized into six sectors by the first ANN of using the dc components, and then the second ANN localizes fault modes by using both the dc and THDs of the d-q axes current in each sector. Simulations and experiments confirm the validity of the proposed method.

Verification code recognition system based on convolutional neural network. In order to strengthen the network security defense work, this paper proposes a novel verification code recognition system based on convolutional neural network. The system combines Internet technology and big data technology, combined with advanced captcha technology, can prevent hackers from brute force cracking behavior to a certain extent. In addition, the system combines convolutional neural network, which makes the verification code combine numbers and letters, which improves the complexity of the verification code and the security of the user account. Based on this, the system uses threshold segmentation method and projection positioning method to construct an 8-layer convolutional neural network model, which enhances the security of the verification code input link. The research results show that the system can enhance the complexity of captcha, improve the recognition rate of captcha, and improve the security of user accounting.

Based on the third generation neural network spiking neural network, this paper optimizes and improves a classification and coding method, and proposes an image recognition method. Firstly, the read image is converted into a spike sequence, and then the spike sequence is encoded in groups and sent to the neurons in the spike neural network. After learning and training for many times, the quantization standard code is obtained. In this process, the spike sequence transformation matrix and dynamic weight matrix are obtained, and the unclassified data are output through the same matrix for image recognition and classification. Simulation results show that the above methods can get correct coding and preliminary recognition classification, and the spiking neural network can be applied.

Malware evolves quickly as new attack, evasion and mutation techniques are commonly used by hackers to build new malicious malware families. For malware detection and classification, multi-class learning model is one of the most popular machine learning models being used. To recognize malicious programs, multi-class model requires malware types to be predefined as output classes in advance which cannot be dynamically adjusted after the model is trained. When a new variant or type of malicious programs is discovered, the trained multi-class model will be no longer valid and have to be retrained completely. This consumes a significant amount of time and resources, and cannot adapt quickly to meet the timely requirement in dealing with dynamically evolving malware types. To cope with the problem, an evolvable malware classification deep learning model, namely EC-Model, is proposed in this paper which can dynamically adapt to new malware types without the need of fully retraining. Consequently, the reaction time can be significantly reduced to meet the timely requirement of malware classification. To our best knowledge, our work is the first attempt to adopt multi-task, deep learning for evolvable malware classification.

Hierarchical Text classification has recently become increasingly challenging with the growing number of classification labels. In this paper, we propose a hierarchical fine-tuning based approach for hierarchical text classification. We use the ordered neurons LSTM (ONLSTM) model by combining the embedding of text and parent category for hierarchical text classification with a large number of categories, which makes full use of the connection between the upper-level and lower-level labels. Extensive experiments show that our model outperforms the state-of-the-art hierarchical model at a lower computation cost.

Deep learning is becoming a basis of decision making systems in many application domains, such as autonomous vehicles, health systems, etc., where the risk of misclassification can lead to serious consequences. It is necessary to know to which extent are Deep Neural Networks (DNNs) robust against various types of adversarial conditions. In this paper, we experimentally evaluate DNNs implemented in embedded device by using laser fault injection, a physical attack technique that is mostly used in security and reliability communities to test robustness of various systems. We show practical results on four activation functions, ReLu, softmax, sigmoid, and tanh. Our results point out the misclassification possibilities for DNNs achieved by injecting faults into the hidden layers of the network. We evaluate DNNs by using several different attack strategies to show which are the most efficient in terms of misclassification success rates. Outcomes of this work should be taken into account when deploying devices running DNNs in environments where malicious attacker could tamper with the environmental parameters that would bring the device into unstable conditions. resulting into faults.

A non-predicted and transient malfunctioning of one or multiple unmanned aerial vehicles (UAVs) is something that may happen over a course of their deployment. Therefore, it is very important to have means to detect these events and take actions for ensuring a high level of reliability, security, and safety of the flight for the predefined mission. In this research, we propose algorithms aiming at the detection and isolation of any faulty UAV so that the performance of the UAVs application is kept at its highest level. To this end, we propose the use of Kullback-Leiler Divergence (KLD) and Artificial Neural Network (ANN) to build algorithms that detect and isolate any faulty UAV. The proposed methods are declined in these two directions: (1) we compute a difference between the internal and external data, use KLD to compute dissimilarities, and detect the UAV that transmits erroneous measurements. (2) Then, we identify the faulty UAV using an ANN model to classify the sensed data using the internal sensed data. The proposed approaches are validated using a real dataset, provided by the Air Lab Failure and Anomaly (ALFA) for UAV fault detection research, and show promising performance.

Industrial Internet of Things (IIoT) has arisen as an emerging trend in the industrial sector. Millions of sensors present in IIoT networks generate a massive amount of data that can open the doors for several cyber-attacks. An intrusion detection system (IDS) monitors real-time internet traffic and identify the behavior and type of network attacks. In this paper, we presented a deep random neural (DRaNN) based scheme for intrusion detection in IIoT. The proposed scheme is evaluated by using a new generation IIoT security dataset UNSW-NB15. Experimental results prove that the proposed model successfully classified nine different types of attacks with a low false-positive rate and great accuracy of 99.54%. To validate the feasibility of the proposed scheme, experimental results are also compared with state-of-the-art deep learning-based intrusion detection schemes. The proposed model achieved a higher attack detection rate of 99.41%.

The paper proposes a method for solving problems of classifying multi-step attacks on wireless sensor networks in the conditions of uncertainty (incompleteness and inconsistency) of the observed signs of attacks. The method aims to eliminate the uncertainty of classification of attacks on networks of this class one the base of the use of neural network approaches to the processing of incomplete and contradictory knowledge on possible attack characteristics. It allows increasing objectivity (accuracy and reliability) of information security monitoring in modern software and hardware systems and Internet of Things networks that actively exploit advantages of wireless sensor networks.

Internet of Things (IoT) development and the addition of billions of computationally limited devices prohibit the use of classical security measures such as Intrusion Detection Systems (IDS). In this paper, we study the influence of the implementation of different feed-forward type of Neural Networks (NNs) on the detection Rate of the Negative Selection Neural Network (NSNN) algorithm. Feed-forward and cascade forward NN structures with different number of neurons and different number of hidden layers are tested. For training and testing the NSNN algorithm the labeled KDD NSL dataset is applied. The detection rates provided by the algorithm with several NN structures to determine the optimal solution are calculated and compared. The results show how these different feed-forward based NN architectures impact the performance of the NSNN algorithm.

Malicious software (malware) is designed to cause unwanted or destructive effects on computers. Since modern society is dependent on computers to function, malware has the potential to do untold damage. Therefore, developing techniques to effectively combat malware is critical. With the rise in popularity of polymorphic malware, conventional anti-malware techniques fail to keep up with the rate of emergence of new malware. This poses a major challenge towards developing an efficient and robust malware detection technique. One approach to overcoming this challenge is to classify new malware among families of known malware. Several machine learning methods have been proposed for solving the malware classification problem. However, these techniques rely on hand-engineered features extracted from malware data which may not be effective for classifying new malware. Deep learning models have shown paramount success for solving various classification tasks such as image and text classification. Recent deep learning techniques are capable of extracting features directly from the input data. Consequently, this paper proposes an end-to-end deep learning framework for multimodels (henceforth, multimodel learning) to solve the challenging malware classification problem. The proposed model utilizes three different deep neural network architectures to jointly learn meaningful features from different attributes of the malware data. End-to-end learning optimizes all processing steps simultaneously, which improves model accuracy and generalizability. The performance of the model is tested with the widely used and publicly available Microsoft Malware Challenge Dataset and is compared with the state-of-the-art deep learning-based malware classification pipeline. Our results suggest that the proposed model achieves comparable performance to the state-of-the-art methods while offering faster training using end-to-end multimodel learning.

In this paper, an Intrusion Detection System (IDS) in the Controller Area Network (CAN) bus of modern vehicles has been proposed. NESLIDS is an anomaly detection algorithm based on the supervised Deep Neural Network (DNN) architecture that is designed to counter three critical attack categories: Denial-of-service (DoS), fuzzy, and impersonation attacks. Our research scope included modifying DNN parameters, e.g. number of hidden layer neurons, batch size, and activation functions according to how well it maximized detection accuracy and minimized the false positive rate (FPR) for these attacks. Our methodology consisted of collecting CAN Bus data from online and in real-time, injecting attack data after data collection, preprocessing in Python, training the DNN, and testing the model with different datasets. Results show that the proposed IDS effectively detects all attack types for both types of datasets. NESLIDS outperforms existing approaches in terms of accuracy, scalability, and low false alarm rates.

Nowadays, the networks attacks became very sophisticated and hard to be recognized, The traditional types of intrusion detection systems became inefficient in predicting new types of attacks. As the IDS is an important factor in securing the network in the real time, many new effective IDS approaches have been proposed. In this paper, we intend to discuss different Artificial Neural Networks based IDS approaches, also we are going to categorize them in four categories (normal ANN, DNN, CNN, RNN) and make a comparison between them depending on different performance parameters (accuracy, FNR, FPR, training time, epochs and the learning rate) and other factors like the network structure, the classification type, the used dataset. At the end of the survey, we will mention the merits and demerits of each approach and suggest some enhancements to avoid the noticed drawbacks.

The new switching architecture of the neural networks was proposed. The switching neural networks consist of the neurons and the switchers. The goal is to reduce expenses on the artificial neural network design and training. For realization of complex models, algorithms and methods of management the neural networks of the big size are required. The number of the interconnection links “everyone with everyone” grows with the number of neurons. The training of big neural networks requires the resources of supercomputers. Time of training of neural networks also depends on the number of neurons in the network. Switching neural networks are divided into fragments connected by the switchers. Training of switcher neuron network is provided by fragments. On the basis of switching neural networks the devices of associative memory were designed with the number of neurons comparable to the human brain.

The object of research is information security. The tools used for research are artificial neural networks. The goal is to increase the cryptography security. The problems are: the big volume of information, the expenses for neural networks design and training. It is offered to use the neural network for the cryptographic transformation of information.

As neural networks make their way into safety-critical systems, where misbehavior can lead to catastrophes, there is a growing interest in certifying the equivalence of two structurally similar neural networks - a problem known as differential verification. For example, compression techniques are often used in practice for deploying trained neural networks on computationally- and energy-constrained devices, which raises the question of how faithfully the compressed network mimics the original network. Unfortunately, existing methods either focus on verifying a single network or rely on loose approximations to prove the equivalence of two networks. Due to overly conservative approximation, differential verification lacks scalability in terms of both accuracy and computational cost. To overcome these problems, we propose NEURODIFF, a symbolic and fine-grained approximation technique that drastically increases the accuracy of differential verification on feed-forward ReLU networks while achieving many orders-of-magnitude speedup. NEURODIFF has two key contributions. The first one is new convex approximations that more accurately bound the difference of two networks under all possible inputs. The second one is judicious use of symbolic variables to represent neurons whose difference bounds have accumulated significant error. We find that these two techniques are complementary, i.e., when combined, the benefit is greater than the sum of their individual benefits. We have evaluated NEURODIFF on a variety of differential verification tasks. Our results show that NEURODIFF is up to 1000X faster and 5X more accurate than the state-of-the-art tool.

Spiking Neural Networks (SNNs) claim to present many advantages in terms of biological plausibility and energy efficiency compared to standard Deep Neural Networks (DNNs). Recent works have shown that DNNs are vulnerable to adversarial attacks, i.e., small perturbations added to the input data can lead to targeted or random misclassifications. In this paper, we aim at investigating the key research question: "Are SNNs secure?" Towards this, we perform a comparative study of the security vulnerabilities in SNNs and DNNs w.r.t. the adversarial noise. Afterwards, we propose a novel black-box attack methodology, i.e., without the knowledge of the internal structure of the SNN, which employs a greedy heuristic to automatically generate imperceptible and robust adversarial examples (i.e., attack images) for the given SNN. We perform an in-depth evaluation for a Spiking Deep Belief Network (SDBN) and a DNN having the same number of layers and neurons (to obtain a fair comparison), in order to study the efficiency of our methodology and to understand the differences between SNNs and DNNs w.r.t. the adversarial examples. Our work opens new avenues of research towards the robustness of the SNNs, considering their similarities to the human brain's functionality.

The age of the wireless network already advances to the fifth generation (5G) era. With software-defined networking (SDN) and network function virtualization (NFV), various scenarios can be implemented in the 5G network. Cloud computing, for example, is one of the important application scenarios for implementing SDN/NFV solutions. The emerging container technologies, such as Docker, can provide more agile service provisioning than virtual machines can do in cloud environments. It is a trend that virtual network functions (VNFs) tend to be deployed in the form of containers. The services provided by clouds can be formed by service function chaining (SFC) consisting of containerized VNFs. Nevertheless, the challenges and limitation regarding SFCs are reported in the literature. Various network services are bound to rely heavily on these novel technologies, however, the development of related technologies often emphasizes functions and ignores security issues. One noticeable issue is the SFC integrity. In brief, SFC integrity concerns whether the paths that traffic flows really pass by and the ones of service chains that are predefined are consistent. In order to examine SFC integrity in the cloud-native environment of 5G network, we propose a framework that can be integrated with NFV management and orchestration (MANO) in this work. The core of this framework is the anomaly detection mechanism for SFC integrity. The learning algorithm of our mechanism is based on extreme learning machine (ELM). The proposed mechanism is evaluated by its performance such as the accuracy of our ELM model. This paper concludes with discussions and future research work.