Biblio

Railroad trespassing is a dangerous activity with significant security and safety risks. However, regular patrolling of potential trespassing sites is infeasible due to exceedingly high resource demands and personnel costs. This raises the need to design automated trespass detection and early warning prediction techniques leveraging state-of-the-art machine learning. To meet this need, we propose a novel framework for Automated Railroad Trespassing detection System using video surveillance data called ARTS. As the core of our solution, we adopt a CNN-based deep learning architecture capable of video processing. However, these deep learning-based methods, while effective, are known to be computationally expensive and time consuming, especially when applied to a large volume of surveillance data. Leveraging the sparsity of railroad trespassing activity, ARTS corresponds to a dual-stage deep learning architecture composed of an inexpensive pre-filtering stage for activity detection, followed by a high fidelity trespass classification stage employing deep neural network. The resulting dual-stage ARTS architecture represents a flexible solution capable of trading-off accuracy with computational time. We demonstrate the efficacy of our approach on public domain surveillance data achieving 0.87 f1 score while keeping up with the enormous video volume, achieving a practical time and accuracy trade-off.

Today, there are several applications which allow us to share images over the internet. All these images must be stored in a secure manner and should be accessible only to the intended recipients. Hence it is of utmost importance to develop efficient and fast algorithms for encryption of images. This paper uses chaotic generators to generate random sequences which can be used as keys for image encryption. These sequences are seemingly random and have statistical properties. This makes them resistant to analysis and correlation attacks. However, these sequences have fixed cycle lengths. This restricts the number of sequences that can be used as keys. This paper utilises neural networks as a source of perturbation in a chaotic generator and uses its output to encrypt an image. The robustness of the encryption algorithm can be verified using NPCR, UACI, correlation coefficient analysis and information entropy analysis.

In this paper, a merged convolution neural network (MCNN) is proposed to improve the accuracy and robustness of real-time facial expression recognition (FER). Although there are many ways to improve the performance of facial expression recognition, a revamp of the training framework and image preprocessing renders better results in applications. When the camera is capturing images at high speed, however, changes in image characteristics may occur at certain moments due to the influence of light and other factors. Such changes can result in incorrect recognition of human facial expression. To solve this problem, we propose a statistical method for recognition results obtained from previous images, instead of using the current recognition output. Experimental results show that the proposed method can satisfactorily recognize seven basic facial expressions in real time.

Deep learning is a popular powerful machine learning solution to the computer vision tasks. The most criticized vulnerability of deep learning is its poor tolerance towards adversarial images obtained by deliberately adding imperceptibly small perturbations to the clean inputs. Such negatives can delude a classifier into wrong decision making. Previous defensive techniques mostly focused on refining the models or input transformation. They are either implemented only with small datasets or shown to have limited success. Furthermore, they are rarely scrutinized from the hardware perspective despite Artificial Intelligence (AI) on a chip is a roadmap for embedded intelligence everywhere. In this paper we propose a new discriminative noise injection strategy to adaptively select a few dominant layers and progressively discriminate adversarial from benign inputs. This is made possible by evaluating the differences in label change rate from both adversarial and natural images by injecting different amount of noise into the weights of individual layers in the model. The approach is evaluated on the ImageNet Dataset with 8-bit truncated models for the state-of-the-art DNN architectures. The results show a high detection rate of up to 88.00% with only approximately 5% of false positive rate for MobileNet. Both detection rate and false positive rate have been improved well above existing advanced defenses against the most practical noninvasive universal perturbation attack on deep learning based AI chip.

In today's society, even though the technology is so developed, the coloring of computer images has remained at the manual stage. As a carrier of human culture and art, film has existed in our history for hundred years. With the development of science and technology, movies have developed from the simple black-and-white film era to the current digital age. There is a very complicated process for coloring old movies. Aside from the traditional hand-painting techniques, the most common method is to use post-processing software for coloring movie frames. This kind of operation requires extraordinary skills, patience and aesthetics, which is a great test for the operator. In recent years, the extensive use of machine learning and neural networks has made it possible for computers to intelligently process images. Since 2016, various types of generative adversarial networks models have been proposed to make deep learning shine in the fields of image style transfer, image coloring, and image style change. In this case, the experiment uses the generative adversarial networks principle to process pictures and videos to realize the automatic rendering of old documentary movies.

Today, network security is a world hot topic in computer security and defense. Intrusions and attacks in network infrastructures lead mostly in huge financial losses, massive sensitive data leaks, thus decreasing efficiency, competitiveness and the quality of productivity of an organization. Network Intrusion Detection System (NIDS) is valuable tool for the defense-in-depth of computer networks. It is widely deployed in network architectures in order to monitor, to detect and eventually respond to any anomalous behavior and misuse which can threat confidentiality, integrity and availability of network resources and services. Thus, the presence of NIDS in an organization plays a vital part in attack mitigation, and it has become an integral part of a secure organization. In this paper, we propose to optimize a very popular soft computing tool widely used for intrusion detection namely Back Propagation Neural Network (BPNN) using a novel hybrid Framework (GASAA) based on improved Genetic Algorithm (GA) and Simulated Annealing Algorithm (SAA). GA is improved through an optimization strategy, namely Fitness Value Hashing (FVH), which reduce execution time, convergence time and save processing power. Experimental results on KDD CUP' 99 dataset show that our optimized ANIDS (Anomaly NIDS) based BPNN, called “ANIDS BPNN-GASAA” outperforms several state-of-art approaches in terms of detection rate and false positive rate. In addition, improvement of GA through FVH has saved processing power and execution time. Thereby, our proposed IDS is very much suitable for network anomaly detection.

Natural language processing is the core of machine translation. In the history, its development process is almost the same as machine translation, and the two complement each other. This article compares the natural language processing of statistical corpora with neural machine translation and concludes the natural language processing: Neural machine translation has the advantage of deep learning, which is very suitable for dealing with the high dimension, label-free and big data of natural language, therefore, its application is more general and reflects the power of big data and big data thinking.

Logistic regression (LR) is used in many areas due to its simplicity and interpretability. While at the same time, those two properties limit its classification accuracy. Deep neural networks (DNNs), instead, achieve state-of-the-art performance in many domains. However, the nonlinearity and complexity of DNNs make it less interpretable. To balance interpretability and classification performance, we propose a novel nonlinear model, Deep Embedding Logistic Regression (DELR), which augments LR with a nonlinear dimension-wise feature embedding. In DELR, each feature embedding is learned through a deep and narrow neural network and LR is attached to decide feature importance. A compact and yet powerful model, DELR offers great interpretability: it can tell the importance of each input feature, yield meaningful embedding of categorical features, and extract actionable changes, making it attractive for tasks such as market analysis and clinical prediction.

With the continuous development of computer network technology, security problems in the network are emerging one after another, and it is becoming more and more difficult to ignore. For the current network administrators, how to successfully prevent malicious network hackers from invading, so that network systems and computers are at Safe and normal operation is an urgent task. This paper proposes a network intrusion detection method based on deep learning. This method uses deep confidence neural network to extract features of network monitoring data, and uses BP neural network as top level classifier to classify intrusion types. The method was validated using the KDD CUP'99 dataset from the Lincoln Laboratory of the Massachusetts Institute of Technology. The results show that the proposed method has a significant improvement over the traditional machine learning accuracy.

In this paper, we introduce a sequential autoencoder framework using long short term memory (LSTM) neural network for computer network intrusion detection. We exploit the dimensionality reduction and feature extraction property of the autoencoder framework to efficiently carry out the reconstruction process. Furthermore, we use the LSTM networks to handle the sequential nature of the computer network data. We assign a threshold value based on cross-validation in order to classify whether the incoming network data sequence is anomalous or not. Moreover, the proposed framework can work on both fixed and variable length data sequence and works efficiently for unforeseen and unpredictable network attacks. We then also use the unsupervised version of the LSTM, GRU, Bi-LSTM and Neural Networks. Through a comprehensive set of experiments, we demonstrate that our proposed sequential intrusion detection framework performs well and is dynamic, robust and scalable.

This paper analyzes information network security risk assessment methods and models. Firstly an improved AHP method is proposed to assign the value of assets for solving the problem of risk judgment matrix consistency effectively. And then the neural network technology is proposed to construct the neural network model corresponding to the risk judgment matrix for evaluating the individual risk of assets objectively, the methods for calculating the asset risk value and system risk value are given. Finally some application results are given. Practice proves that the methods are correct and effective, which has been used in information network security risk assessment application and offers a good foundation for the implementation of the automatic assessment.

Network situation value is an important index to measure network security. Establishing an effective network situation prediction model can prevent the occurrence of network security incidents, and plays an important role in network security protection. Through the understanding and analysis of the network security situation, we can see that there are many factors affecting the network security situation, and the relationship between these factors is complex., it is difficult to establish more accurate mathematical expressions to describe the network situation. Therefore, this paper uses the grey neural network as the prediction model, but because the convergence speed of the grey neural network is very fast, the network is easy to fall into local optimum, and the parameters can not be further modified, so the Multi-Swarm Chaotic Particle Optimization (MSCPO)is used to optimize the key parameters of the grey neural network. By establishing the nonlinear mapping relationship between the influencing factors and the network security situation, the network situation can be predicted and protected.

Fully connected autonomous vehicles are more vulnerable than ever to hacking and data theft. The controller area network (CAN) protocol is used for communication between in-vehicle control networks (IVN). The absence of basic security features of this protocol, like message authentication, makes it quite vulnerable to a wide range of attacks including spoofing attacks. As traditional cybersecurity methods impose limitations in ensuring confidentiality and integrity of transmitted messages via CAN, a new technique has emerged among others to approve its reliability in fully authenticating the CAN messages. At the physical layer of the communication system, the method of fingerprinting the messages is implemented to link the received signal to the transmitting electronic control unit (ECU). This paper introduces a new method to implement the security of modern electric vehicles. The lumped element model is used to characterize the channel-specific step response. ECU and channel imperfections lead to a unique transfer function for each transmitter. Due to the unique transfer function, the step response for each transmitter is unique. In this paper, we use control system parameters as a feature-set, afterward, a neural network is used transmitting node identification for message authentication. A dataset collected from a CAN network with eight-channel lengths and eight ECUs to evaluate the performance of the suggested method. Detection results show that the proposed method achieves an accuracy of 97.4% of transmitter detection.

This paper provides an approach to the detection of information security breaches in automated process control systems (APCS), which consists in forecasting multivariate time series formed from the values of the operating parameters of the end system devices. Using an experimental model of water treatment, a comparison was made of the forecasting results for the parameters characterizing the operation of the entire model, and for the parameters characterizing the flow of individual subprocesses implemented by the model. For forecasting, GRU-neural network training was performed.

To be prepared against cyberattacks, most organizations resort to security information and event management systems to monitor their infrastructures. These systems depend on the timeliness and relevance of the latest updates, patches and threats provided by cyberthreat intelligence feeds. Open source intelligence platforms, namely social media networks such as Twitter, are capable of aggregating a vast amount of cybersecurity-related sources. To process such information streams, we require scalable and efficient tools capable of identifying and summarizing relevant information for specified assets. This paper presents the processing pipeline of a novel tool that uses deep neural networks to process cybersecurity information received from Twitter. A convolutional neural network identifies tweets containing security-related information relevant to assets in an IT infrastructure. Then, a bidirectional long short-term memory network extracts named entities from these tweets to form a security alert or to fill an indicator of compromise. The proposed pipeline achieves an average 94% true positive rate and 91% true negative rate for the classification task and an average F1-score of 92% for the named entity recognition task, across three case study infrastructures.

Conventional methods for anomaly detection include techniques based on clustering, proximity or classification. With the rapidly growing social networks, outliers or anomalies find ingenious ways to obscure themselves in the network and making the conventional techniques inefficient. In this paper, we utilize the ability of Deep Learning over topological characteristics of a social network to detect anomalies in email network and twitter network. We present a model, Graph Neural Network, which is applied on social connection graphs to detect anomalies. The combinations of various social network statistical measures are taken into account to study the graph structure and functioning of the anomalous nodes by employing deep neural networks on it. The hidden layer of the neural network plays an important role in finding the impact of statistical measure combination in anomaly detection.

In this paper, it first analyzed the characteristics of Advanced Persistent Threat (APT). according to APT attack, this paper established an BP neural network optimized by improved adaptive genetic algorithm to predict the security risk of nodes in the network. and calculated the path of APT attacks with the maximum possible attack. Finally, experiments verify the effectiveness and correctness of the algorithm by simulating attacks. Experiments show that this model can effectively evaluate the security situation in the network, For the defenders to adopt effective measures defend against APT attacks, thus improving the security of the network.

As we all know, computer network security evaluation is an important link in the field of network security. Traditional computer network security evaluation methods use BP neural network combined with network security standards to train and simulate. However, because BP neural network is easy to fall into local minimum point in the training process, the evalu-ation results are often inaccurate. In this paper, the LM (Levenberg-Marquard) algorithm is used to optimize the BP neural network. The LM-BP algorithm is constructed and applied to the computer network security evaluation. The results show that compared with the traditional evaluation algorithm, the optimized neural network has the advantages of fast running speed and accurate evaluation results.

Flow-based network attack detection technology is able to identify many threats in network traffic. Existing techniques have several drawbacks: i) rule-based approaches are vulnerable because it needs all the signatures defined for the possible attacks, ii) anomaly-based approaches are not efficient because it is easy to find ways to launch attacks that bypass detection, and iii) both rule-based and anomaly-based approaches heavily rely on domain knowledge of networked system and cyber security. The major challenge to existing methods is to understand novel attack scenarios and design a model to detect novel and more serious attacks. In this paper, we investigate network attacks and unveil the key activities and the relationships between these activities. For that reason, we propose methods to understand the network security practices using theoretic concepts such as graph kernels. In addition, we integrate graph kernels over deep learning architecture to exploit the relationship expressiveness among network flows and combine ability of deep neural networks (DNNs) with deep architectures to learn hidden representations, based on the communication representation graph of each network flow in a specific time interval, then the flow-based network attack detection can be done effectively by measuring the similarity between the graphs to two flows. The proposed study provides the effectiveness to obtain insights about network attacks and detect network attacks. Using two real-world datasets which contain several new types of network attacks, we achieve significant improvements in accuracies over existing network attack detection tasks.

With the remarkable success of deep learning, Deep Neural Networks (DNNs) have been applied as dominant tools to various machine learning domains. Despite this success, however, it has been found that DNNs are surprisingly vulnerable to malicious attacks; adding a small, perceptually indistinguishable perturbations to the data can easily degrade classification performance. Adversarial training is an effective defense strategy to train a robust classifier. In this work, we propose to utilize the generator to learn how to create adversarial examples. Unlike the existing approaches that create a one-shot perturbation by a deterministic generator, we propose a recursive and stochastic generator that produces much stronger and diverse perturbations that comprehensively reveal the vulnerability of the target classifier. Our experiment results on MNIST and CIFAR-10 datasets show that the classifier adversarially trained with our method yields more robust performance over various white-box and black-box attacks.

As a cyber attack which leverages social engineering and other sophisticated techniques to steal sensitive information from users, phishing attack has been a critical threat to cyber security for a long time. Although researchers have proposed lots of countermeasures, phishing criminals figure out circumventions eventually since such countermeasures require substantial manual feature engineering and can not detect newly emerging phishing attacks well enough, which makes developing an efficient and effective phishing detection method an urgent need. In this work, we propose a novel phishing website detection approach by detecting the Uniform Resource Locator (URL) of a website, which is proved to be an effective and efficient detection approach. To be specific, our novel capsule-based neural network mainly includes several parallel branches wherein one convolutional layer extracts shallow features from URLs and the subsequent two capsule layers generate accurate feature representations of URLs from the shallow features and discriminate the legitimacy of URLs. The final output of our approach is obtained by averaging the outputs of all branches. Extensive experiments on a validated dataset collected from the Internet demonstrate that our approach can achieve competitive performance against other state-of-the-art detection methods while maintaining a tolerable time overhead.

With the developments in deep learning, the security of neural networks against vulnerabilities has become one of the most urgent research topics in deep learning. There are many types of security countermeasures. Adversarial examples and their defense methods, in particular, have been well-studied in recent years. An adversarial example is designed to make neural networks misclassify or produce inaccurate output. Audio adversarial examples are a type of adversarial example where the main target of attack is a speech-to-text transcription neural network. In this study, we propose a new defense method against audio adversarial examples for the speech-to-text transcription neural networks. It is difficult to determine whether an input waveform data representing the sound of voice is an audio adversarial example. Therefore, the main framework of the proposed defense method is based on a sandbox approach. To evaluate the proposed defense method, we used actual audio adversarial examples that were created on Deep Speech, which is a speech-to-text transcription neural network. We confirmed that our defense method can identify audio adversarial examples to protect speech-to-text systems.

With the development of technology, the massive malware become the major challenge to current computer security. In our work, we implemented a malware detection system using deep learning on API calls. By means of cuckoo sandbox, we extracted the API calls sequence of malicious programs. Through filtering and ordering the redundant API calls, we extracted the valid API sequences. Compared with GRU, BGRU, LSTM and SimpleRNN, we evaluated the BLSTM on the massive datasets including 21,378 samples. The experimental results demonstrate that BLSTM has the best performance for malware detection, reaching the accuracy of 97.85%.

Vehicular networks are susceptible to variety of attacks such as denial of service (DoS) attack, sybil attack and false alert generation attack. Different cryptographic methods have been proposed to protect vehicular networks from these kind of attacks. However, cryptographic methods have been found to be less effective to protect from insider attacks which are generated within the vehicular network system. Misbehavior detection system is found to be more effective to detect and prevent insider attacks. In this paper, we propose a machine learning based misbehavior detection system which is trained using datasets generated through extensive simulation based on realistic vehicular network environment. The simulation results demonstrate that our proposed scheme outperforms previous methods in terms of accurately identifying various misbehavior.

Internet of Things is nowadays growing faster than ever before. Operators are planning or already creating dedicated networks for this type of devices. There is a need to create dedicated solutions for this type of network, especially solutions related to information security. In this article we present a mechanism of security-aware routing, which takes into account the evaluation of trust in devices and packet flows. We use trust relationships between flows and network nodes to create secure SDN paths, not ignoring also QoS and energy criteria. The system uses SDN infrastructure, enriched with Cognitive Packet Networks (CPN) mechanisms. Routing decisions are made by Random Neural Networks, trained with data fetched with Cognitive Packets. The proposed network architecture, implementing the security-by-design concept, was designed and is being implemented within the SerIoT project to demonstrate secure networks for the Internet of Things (IoT).