Biblio

In this paper, new image encryption based on singular value decomposition (SVD), fractional discrete cosine transform (FrDCT) and the chaotic system is proposed for the security of medical image. Reliability, vitality, and efficacy of medical image encryption are strengthened by it. The proposed method discusses the benefits of FrDCT over fractional Fourier transform. The key sensitivity of the proposed algorithm for different medical images inspires us to make a platform for other researchers. Theoretical and statistical tests are carried out demonstrating the high-level security of the proposed algorithm.

A term systems of systems (SoS) refers to a setup in which a number of independent systems collaborate to create a value that each of them is unable to achieve independently. Complexity of a SoS structure is higher compared to its constitute systems that brings challenges in analyzing its critical properties such as security. An SoS can be seen as a set of connected systems or services that needs to be adequately protected. Communication between such systems or services can be considered as a service itself, and it is the paramount for establishment of a SoS as it enables connections, dependencies, and a cooperation. Given that reliable and predictable communication contributes directly to a correct functioning of an SoS, communication as a service is one of the main assets to consider. Protecting it from malicious adversaries should be one of the highest priorities within SoS design and operation. This study aims to investigate the attack propagation problem in terms of service-guarantees through the decomposition into sub-services enriched with preconditions and postconditions at the service levels. Such analysis is required as a prerequisite for an efficient SoS risk assessment at the design stage of the SoS development life cycle to protect it from possibly high impact attacks capable of affecting safety of systems and humans using the system.

In order to solve the problem that there is no effective means to find the optimal number of hidden nodes of single-hidden-layer feedforward neural network, in this paper, a method will be introduced to solve it effectively by using singular value decomposition. First, the training data need to be normalized strictly by attribute-based data normalization and sample-based data normalization. Then, the normalized data is decomposed based on the singular value decomposition, and the number of hidden nodes is determined according to main eigenvalues. The experimental results of MNIST data set and APS data set show that the feedforward neural network can attain satisfactory performance in the classification task.

In the modern security-conscious world, Deep Packet Inspection (DPI) proxies are increasingly often used on industrial and enterprise networks to perform TLS unwrapping on all outbound connections. However, enabling TLS unwrapping requires local devices to have the DPI proxy Certificate Authority certificates installed. While for conventional computing devices this is addressed via enterprise management, it's a difficult problem for Internet of Things ("IoT") devices which are generally not under enterprise management, and may not even be capable of it due to their resource-constrained nature. Thus, for typical IoT devices, being installed on a network with DPI requires either manual device configuration or custom DPI proxy configuration, both of which solutions have significant shortcomings. This poses a serious challenge to the deployment of IoT devices on DPI-enabled intranets. The authors propose a solution to this problem: a method of installing on IoT devices the CA certificates for DPI proxy CAs, as well as other security configuration ("security bootstrapping"). The proposed solution respects the DPI policies, while allowing the commissioning of IoT and IIoT devices without the need for additional manual configuration either at device scope or at network scope. This is accomplished by performing the bootstrap operation over unsecured connection, and downloading certificates using TLS validation at application level. The resulting solution is light-weight and secure, yet does not require validation of the DPI proxy's CA certificates in order to perform the security bootstrapping, thus avoiding the chicken-and-egg problem inherent in using TLS on DPI-enabled intranets.

With the growing number of streaming services, internet providers are increasingly needing to be able to identify the types of data and content providers that are being used on their networks. Traditional methods, such as IP and port scanning, are not always available for clients using VPNs or with providers using varying IP addresses. As such, in this paper we explore a potential method using neural networks and Markov Decision Process in order to augment deep packet inspection techniques in identifying the source and class of video streaming services.

Deep packet inspection via regular expression (RE) matching is a crucial task of network intrusion detection systems (IDSes), which secure Internet connection against attacks and suspicious network traffic. Monitoring high-speed computer networks (100 Gbps and faster) in a single-box solution demands that the RE matching, traditionally based on finite automata (FAs), is accelerated in hardware. In this paper, we describe a novel FPGA architecture for RE matching that is able to process network traffic beyond 100 Gbps. The key idea is to reduce the required FPGA resources by leveraging approximate nondeterministic FAs (NFAs). The NFAs are compiled into a multi-stage architecture starting with the least precise stage with a high throughput and ending with the most precise stage with a low throughput. To obtain the reduced NFAs, we propose new approximate reduction techniques that take into account the profile of the network traffic. Our experiments showed that using our approach, we were able to perform matching of large sets of REs from SNORT, a popular IDS, on unprecedented network speeds.

Virtual platforms provide a full hardware/software platform to study device limitations in an early stages of the design flow and to develop software without requiring a physical implementation. This paper describes the development process of a virtual platform for Deep Packet Inspection (DPI) hardware accelerators by using Transaction Level Modeling (TLM). We propose two DPI architectures oriented to System-on-Chip FPGA. The first architecture, CPU-DMA based architecture, is a hybrid CPU/FPGA where the packets are filtered in the software domain. The second architecture, Hardware-IP based architecture, is mainly implemented in the hardware domain. We have created two virtual platforms and performed the simulation, the debugging and the analysis of the hardware/software features, in order to compare results for both architectures.

Deep learning has undergone tremendous advancements in computer vision studies. The training of deep learning neural networks depends on a considerable amount of ground truth datasets. However, labeling ground truth data is a labor-intensive task, particularly for large-volume video analytics applications such as video surveillance and vehicles detection for autonomous driving. This paper presents a rapid and accurate method for associative searching in big image data obtained from security monitoring systems. We developed a semi-automatic moving object annotation method for improving deep learning models. The proposed method comprises three stages, namely automatic foreground object extraction, object annotation in subsequent video frames, and dataset construction using human-in-the-loop quick selection. Furthermore, the proposed method expedites dataset collection and ground truth annotation processes. In contrast to data augmentation and data generative models, the proposed method produces a large amount of real data, which may facilitate training results and avoid adverse effects engendered by artifactual data. We applied the constructed annotation dataset to train a deep learning you-only-look-once (YOLO) model to perform vehicle detection on street intersection surveillance videos. Experimental results demonstrated that the accurate detection performance was improved from a mean average precision (mAP) of 83.99 to 88.03.

We consider the problem of attack detection for IoT networks based only on passively collected network parameters. For the first time in the literature, we develop a blind attack detection method based on data conformity evaluation. Network parameters collected passively, are converted to their conformity values through iterative projections on refined L1-norm tensor subspaces. We demonstrate our algorithmic development in a case study for a simulated star topology network. Type of attack, affected devices, as well as, attack time frame can be easily identified.

Anomaly detection generally involves the extraction of features from entities' or users' properties, and the design of anomaly detection models using machine learning or deep learning algorithms. However, only considering entities' property information could lead to high false positives. We posit the importance of also considering connections or relationships between entities in the detecting of anomalous behaviors and associated threat groups. Therefore, in this paper, we design a GCN (graph convolutional networks) based anomaly detection model to detect anomalous behaviors of users and malicious threat groups. The GCN model could characterize entities' properties and structural information between them into graphs. This allows the GCN based anomaly detection model to detect both anomalous behaviors of individuals and associated anomalous groups. We then evaluate the proposed model using a real-world insider threat data set. The results show that the proposed model outperforms several state-of-art baseline methods (i.e., random forest, logistic regression, SVM, and CNN). Moreover, the proposed model can also be applied to other anomaly detection applications.

In this work, we will present a new hybrid cryptography method based on two hard problems: 1- The problem of the discrete logarithm on an elliptic curve defined on a finite local ring. 2- The closest vector problem in lattice and the conjugate problem on square matrices. At first, we will make the exchange of keys to the Diffie-Hellman. The encryption of a message is done with a bad basis of a lattice.

The article explores the question of the effective implementation of arithmetic operations with points of an elliptic curve given over a prime field. Given that the basic arithmetic operations with points of an elliptic curve are the operations of adding points and doubling points, we study the question of implementing the arithmetic operations of adding and doubling points in various coordinate systems using the weighted number system and using the Residue Number System (RNS). We have shown that using the fourmodule RNS allows you to get an average gain for the operation of adding points of the elliptic curve of 8.67% and for the operation of doubling the points of the elliptic curve of 8.32% compared to the implementation using the operation of modular multiplication with special moduli from NIST FIPS 186.

This paper presents the encryption of advanced pictures dependent on turmoil hypothesis. Two principal forms are incorporated into this method those are pixel rearranging and pixel substitution. Disorder hypothesis is a part of science concentrating on the conduct of dynamical frameworks that are profoundly touchy to beginning conditions. A little change influences the framework to carry on totally unique, little changes in the beginning position of a disorganized framework have a major effect inevitably. A key of 128-piece length is created utilizing mayhem hypothesis, and decoding should be possible by utilizing a similar key. The bit-XOR activity is executed between the unique picture and disorder succession x is known as pixel substitution. Pixel rearranging contains push savvy rearranging and section astute rearranging gives extra security to pictures. The proposed strategy for encryption gives greater security to pictures.

Unauthorized access of the data is one of the major threat for the real world digital data communication. Digital images are one of the most vital subset of the digital data. Several important and sensitive information is conveyed through digital images. Hence, digital image security is one of the foremost interest of the researchers. Cryptographic algorithms Biological sequences are often used to encrypt data due to their inherent features. DNA encryption is one of the widely used method used for data security which is based on the properties of the biological sequences. To protect the images from unwanted accesses, a new two stage method is proposed in this work. DNA Encryption and Polymerase Chain Reaction (PCR) Amplification is used to enhance the security. The proposed method is evaluated using different standard parameters that shows the efficiency of the algorithm.

We consider a one-time digital signature scheme recently proposed by Persichetti and show that a successful key recovery attack can be mounted with limited complexity. The attack we propose exploits a single signature intercepted by the attacker, and relies on a statistical analysis performed over such a signature, followed by information set decoding. We assess the attack complexity and show that a full recovery of the secret key can be performed with a work factor that is far below the claimed security level. The efficiency of the attack is motivated by the sparsity of the signature, which leads to a significant information leakage about the secret key.

SM2 is an elliptic curve public key cryptography algorithm released by the State Cryptography Administration of China. It includes digital signature, data encryption and key exchange schemes. To meet specific application requirements, such as to protect the user's private key in software only implementation, and to facilitate secure cloud cryptography computing, secret sharing based SM2 signature generation schemes have been proposed in the literature. In this paper a new such kind of scheme based upon additively homomorphic encryption is proposed. The proposed scheme overcomes the drawback that the existing schemes have and is more secure. It is useful in various application scenarios.

Considering the security of message exchange between service robot and cloud, we propose to authenticate the message integrity based on RSA algorithm and digital signature. In the process of message transmission, RSA algorithm is used to encrypt message for service robot and decrypt message for cloud. The digital signature algorithm is used to authenticate the source of the message. The results of experiment have proved that the proposed scheme can guarantee the security of message transmission.

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 based facial expression recognition (FER) has received a lot of attention in the past few years. Most of the existing deep learning based FER methods do not consider domain knowledge well, which thereby fail to extract representative features. In this work, we propose a novel FER framework, named Facial Motion Prior Networks (FMPN). Particularly, we introduce an addition branch to generate a facial mask so as to focus on facial muscle moving regions. To guide the facial mask learning, we propose to incorporate prior domain knowledge by using the average differences between neutral faces and the corresponding expressive faces as the training guidance. Extensive experiments on three facial expression benchmark datasets demonstrate the effectiveness of the proposed method, compared with the state-of-the-art approaches.

In the past few years, there has been increasing interest in the perception of human expressions and mental states by machines, and Facial Expression Recognition (FER) has attracted increasing attention. Facial Action Unit (AU) is an early proposed method to describe facial muscle movements, which can effectively reflect the changes in people's facial expressions. In this paper, we propose a high-performance facial expression recognition method based on facial action unit, which can run on low-configuration computer and realize video and real-time camera FER. Our method is mainly divided into two parts. In the first part, 68 facial landmarks and image Histograms of Oriented Gradients (HOG) are obtained, and the feature values of action units are calculated accordingly. The second part uses three classification methods to realize the mapping from AUs to FER. We have conducted many experiments on the popular human FER benchmark datasets (CK+ and Oulu CASIA) to demonstrate the effectiveness of our method.

In the era of the ever-growing number of smart devices, fraudulent practices through Phishing Websites have become an increasingly severe threat to modern computers and internet security. These websites are designed to steal the personal information from the user and spread over the internet without the knowledge of the user using the system. These websites give a false impression of genuinity to the user by mirroring the real trusted web pages which then leads to the loss of important credentials of the user. So, Detection of such fraudulent websites is an essence and the need of the hour. In this paper, various classifiers have been considered and were found that ensemble classifiers predict to utmost efficiency. The idea behind was whether a combined classifier model performs better than a single classifier model leading to a better efficiency and accuracy. In this paper, for experimentation, three Meta Classifiers, namely, AdaBoostM1, Stacking, and Bagging have been taken into consideration for performance comparison. It is found that Meta Classifier built by combining of simple classifier(s) outperform the simple classifier's performance.

Due to practical constraints in preventing phishing through public network or insecure communication channels, simple physical unclonable function (PDF)-based authentication protocol with unrestricted queries and transparent responses is vulnerable to modeling and replay attacks. In this paper, we present a PUF-based authentication method to mitigate the practical limitations in applications where a resource-rich server authenticates a device with no strong restriction imposed on the type of PUF designs or any additional protection on the binary channel used for the authentication. Our scheme uses an active deception protocol to prevent machine learning (ML) attacks on a device. The monolithic system makes collection of challenge response pairs (CRPs) easy for model building during enrollment but prohibitively time consuming upon device deployment. A genuine server can perform a mutual authentication with the device at any time with a combined fresh challenge contributed by both the server and the device. The message exchanged in clear does not expose the authentic CRPs. The false PUF multiplexing is fortified against prediction of waiting time by doubling the time penalty for every unsuccessful authentication.

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.

Modern large scale technical systems often face iterative changes on their behaviours with the requirement of validated quality which is not easy to achieve completely with traditional testing. Regression verification is a powerful tool for the formal correctness analysis of software-driven systems. By proving that a new revision of the software behaves similarly as the original version of the software, some of the trust that the old software and system had earned during the validation processes or operation histories can be inherited to the new revision. This trust inheritance by the formal analysis relies on a number of implicit assumptions which are not self-evident but easy to miss, and may lead to a false sense of safety induced by a misunderstood regression verification processes. This paper aims at pointing out hidden, implicit assumptions of regression verification in the context of cyber-physical systems by making them explicit using practical examples. The explicit trust inheritance analysis would clarify for the engineers to understand the extent of the trust that regression verification provides and consequently facilitate them to utilize this formal technique for the system validation.

We consider distributed Kalman filter for dynamic state estimation over wireless sensor networks. It is promising but challenging when network is under cyber attacks. Since the information exchange between nodes, the malicious attacks quickly spread across the entire network, which causing large measurement errors and even to the collapse of sensor networks. Aiming at the malicious network attack, a trust-based distributed processing frame is proposed. Which allows neighbor nodes to exchange information, and a series of trusted nodes are found using truth discovery. As a demonstration, distributed Cooperative Localization is considered, and numerical results are provided to evaluate the performance of the proposed approach by considering random, false data injection and replay attacks.