Authentication Algorithm Research Articles

Preventing DeepFake Attacks on Speaker Authentication by Dynamic Lip Movement Analysis

Recent research has demonstrated that lip-based speaker authentication systems can not only achieve good authentication performance but also guarantee liveness. However, with modern DeepFake technology, attackers can produce the talking video of a user without leaving any visually noticeable fake traces. This can seriously compromise traditional face-based or lip-based authentication systems. To defend against sophisticated DeepFake attacks, a new visual speaker authentication scheme based on the deep convolutional neural network (DCNN) is proposed in this paper. The proposed network is composed of two functional parts, namely, the Fundamental Feature Extraction network (FFE-Net) and the Representative lip feature extraction and Classification network (RC-Net). The FFE-Net provides the fundamental information for speaker authentication. As the static lip shape and lip appearance is vulnerable to DeepFake attacks, the dynamic lip movement is emphasized in the FFE-Net. The RC-Net extracts high-level lip features that discriminate against human imposters while capturing the client's talking style. A multi-task learning scheme is designed, and the proposed network is trained end-to-end. Experiments on the GRID and MOBIO datasets have demonstrated that the proposed approach is able to achieve an accurate authentication result against human imposters and is much more robust against DeepFake attacks compared to three state-of-the-art visual speaker authentication algorithms. It is also worth noting that the proposed approach does not require any prior knowledge of the DeepFake spoofing method and thus can be applied to defend against different kinds of DeepFake attacks.

Сравнение применения локальных и глобальных признаков рукописной подписи для аутентификации пользователя

The paper compares two methods of user authentication based on a handwritten signature. The first is based on the extraction of local signature features as functions that depend on the time of its application. The second extracts global signature features that characterize it entirely without reference to the moments of application. Authentication algorithms are presented for each of the methods; experiments are carried out on real handwritten signatures obtained during the study.

A Study on the Concept of Using Efficient Lightweight Hash Chain to Improve Authentication in VMF Military Standard

Authentication algorithms in the form of cryptographic schemes, such as the Secure Hash Algorithm 1 (SHA-1) and the digital signature algorithm (DSA), specified in the current variable message format (VMF) military standard have numerous reliability-related limitations when applied to tactical data link (TDL) and multi-TDL networks (MTN). This is because TDL and MTN require maximum tactical security, communication integrity, and low network overhead based on many protocol header bits for rapid communication with limited network resources. The application of such authentication algorithms to TDL and MTN in a rapidly changing battlefield environment without reinforcement measures will lead to functional weaknesses and vulnerabilities when high-level digital-covert activities and deception tactics are implemented. Consequently, the existing VMF authentication scheme must be improved to secure transmission integrity, lower network transaction, and receive authentication tactical information in VMF-based combat network radio (CNR) networks. Therefore, in this study, a tactical wireless ad hoc network topology, similar to that of the existing CNRs, is considered, and a lightweight multi-factor hash chain-based authentication scheme that includes a time-based one-time password (T-OTP) for network overhead reduction and terminal authentication is proposed, coupled with exception handling. The proposed method enhances the confidentiality of tactical message exchanges and reduces unnecessary network transactions and transmission bits for authentication flows between real-time military terminals owned by squads, while ensuring robustness in limited battlefields. Based on these approaches, in the future, we intend to increase the authentication reliability between wireless terminals in the Korean variable message format (KVMF)-based CNR networks based on the Korean Army Corps network scenarios.

Blockchain-Based Secure Mist Computing Network Architecture for Intelligent Transportation Systems

Conventional centralized architectures are sufficiently educated to provide high scalability, availability, and low latency and bandwidth usages for the Internet of Things (IoT) network. The exponential increase in volume and number of IoT devices in Intelligent Transportation Systems (ITS) turns our physical world into the cyber world. Security and privacy in the ITS network have become the main concern. To address these issues and challenges, a secure distributed mist computing network architecture for ITS is proposed by leveraging the features of blockchain technology. In this model, we present IoT user/device registration and authentication algorithms and enable the computing resources at the extreme edge of the network by deploying a smart contract. The proposed model uses an aggregate signature scheme to generate a signature for multiple IoT devices. To evaluate the proposed model, we performed an experimental analysis based on various performance measures. The proposed model gains 81% of lower median latency at local nodes compared to the core model. The result shows that the model performed effectively and a suitable solution for various ITS applications.

A Robust Authentication Algorithm for Medical Images Based on Fractal Brownian Model and Visual Cryptography

In this paper, we aimed to discuss the security authentication requirements of medical images in the medical network, and a security authentication method is designed based on fractal and visual cryptography. Based on the discrete fractal Brownian random field model, the gray-level statistical information and spatial structure information of medical images is fully mined. The gray distribution of medical images is expressed in the form of fractal features. By using the spatial data mining methods, the data of fractal structure space is analyzed, and by using the stability of the energy structure, the authentication features are formed. Using the visual cryptography (VC), the robustness of the authentication method is further enhanced. Through the centralized test of common medical images and the comparison analysis with existing methods, it is further verified that the method is effective against common attacks such as JPEG compression, scaling, rotation operation, clipping, added noise, filtering, and blurring.

Biometric authenticator algorithm based on multiresolution analysis

Features extraction is an essential process in identifying person biometrics because the effectiveness of the system depends on it. Multiresolution Analysis success can be used in the system of a person’s identification and pattern recognition. In this paper, we present a feature extraction method for two-dimensional face and iris authentication. Our approach is a combination of principal component analysis (PCA) and curvelet transform as an improved fusion approach for feature extraction. The proposed fusion approach involves image denoising using 2D-Curvelet transform to achieve compact representations of curves singularities. This is followed by the application of PCA as a fusion rule to improve upon the spatial resolution. The limitations of the only PCA algorithm are a poor recognition speed and complex mathematical calculating load, to reduce these limitations, we are applying the curvelet transform. <br /> To assess the performance of the presented method, we have employed three classification techniques: Neural networks (NN), K-Nearest Neighbor (KNN) and Support Vector machines (SVM).<br />The results reveal that the extraction of image features is more efficient using Curvelet/PCA.

A secure vehicle theft detection framework using Blockchain and smart contract

Nowadays, vehicle theft has been increased drastically all over the world. The prevention of vehicle theft is essential to enhance vehicle security. A large number of vehicles have been stolen for the lack of essential foundation and administration of a secure platform. Several existing systems were developed to protect the vehicle from unauthorized access. But, they suffer from various limitations such as data security, the possibility of cybercriminals activities, leakage of personal information, and centralized System. We propose a vehicle theft detection framework using a decentralized and secure platform to increase the security level of the vehicle. Blockchain and smart contracts are used to provide the security of the stored data on the ledger and authenticate a genuine user automatically with greater accuracy. In this paper, we present 2-Step Authentication (2SA) and unauthorized access detection algorithms. The 2SA ensures the secure accessibility of the application by providing the randomly token chosen by the user. The proposed framework can provide vehicle security and owner’s privacy. In this proposed framework, more than one person can drive the vehicle authorizing by the vehicle owner without hampering stored data in the vehicle device.

Face Authenticated Hand Gesture Based Human Computer Interaction for Desktops

Abstract Hand gesture detection and recognition is a cutting-edge technology that is getting progressively applicable in several applications, including the recent trends namely Virtual Reality and Augmented Reality. It is a key part of Human-Computer Interaction which gives an approach to two-way interaction between the computer and the user. Currently, this technology is limited to expensive and highly specialized equipment and gadgets such as Kinect and the Oculus Rift. In this paper, various technologies and methodologies of implementing a gesture detection and recognition system are discussed. The paper also includes the implementation of a face recognition module using the Viola-Jones Algorithm for authentication of the system followed by hand gesture recognition using CNN to perform basic operations on the laptop. Any type of user can use gesture control as an alternative and interesting way to control their laptop. Furthermore, this can be used as a prototype for future implementations in the field of virtual reality as well as augmented reality.

МЕТОД ПРЕОБРАЗОВАНИЯ СЕМАНТИЧЕСКОЙ СЕТИ ДЛЯ АВТОМАТИЗАЦИИ ОЦЕНИВАНИЯ РЕШЕНИЯ ЗАДАЧ ПО ПРОГРАММИРОВАНИЮ В ПРОЦЕССЕ ЭЛЕКТРОННОГО ОБУЧЕНИЯ

The article presents a semantic network transformation method for a programcode into an N-dimensional vector. The proposed method allows automating the quality assessment of solving programming problems in the process of e-learning. The method includes the authentic algorithms of building and converting the network. In order to determine the algorithm in the program code there is a template of this algorithm, presented in the form of a subgraph of abstract concepts of the language in the semantic network, built on the basis of this code. The search for the algorithm by comparing the subgraph of the network with the template network helped to identify the BFS algorithm with a given accuracy: the cutoff threshold for the perceptron outputs is 0.85, which is based on the calculation of accuracy of the single-layer perceptron in the classification of the MNIST base equal to 88%, which confirms the effectiveness of the developed method and requires further research using machine learning methods to find the optimal value of the coordinates of the nodes of the semantic network and templates of algorithms.

Research perceptions on ransomware attack: a complete analysis on conventional authentication protocols in network

Nowadays, Computer Networks and the internet is on the increase due to the precedence that provided by them. An enormous amount of information is accessed and allowed the users to share the information on an incredible scale while connecting the network to the Internet. Even though the internet nature crafts more benefits, still it is posed by the limitations because of the attacks. One of the special types of malicious software (attack) is ransomware also called malware that affects the systems and restricts the user’s access over the system. Further, it files till the payment of ransom. This malware is made by locking the user’s desktop and encrypting the user’s files. This has emerged as a critical threat in network security since each day the raising of ransomware gets abundant. Hence, the prediction of ransomware is considered as the major problem by the researchers and numerous researches are going on over this issue. This survey planned to review the network security models along with the authentication protocol. More importantly, the ransomware attack is also highly concentrated in this survey. Further, the literature analyses on diverse techniques under network security are made. Then the analysis also focused on the algorithms used and is categorized as protocols, authentication algorithms, optimization algorithms, and other techniques. Moreover, this survey demonstrates a detailed review of the cryptographic techniques, attacks, simulation tools and clouds that are exploited in the reviewed papers. Additionally, the chronological review and the performance are reviewed under the network security models. Finally, this paper exploits the research and described the challenges on the network security that can be used further in the future

IoT security system with modified Zero Knowledge Proof algorithm for authentication

It has been predicted that more devices will be connected to the internet network along with the development of IoT, and that will increase the complexity in the security system. The most important thing in security systems is the process of encryption and authentication. Various encryption techniques are developed to overcome security problems of the data. One of the methods used for authentication of data is Zero Knowledge Proof. This method works to identify the authenticity of someones statement to proof without showing any knowledge of the statement mentioned. This research will mainly discuss about the security of data transmission system by combining data encryption and data authentication. The proposed data encryption is using Advanced Encryption System and method for authentication of data using the Zero Knowledge Proof. This research will conduct the development methods of authentication Zero Knowledge Proof from previous research and the result was compared with the proposed method based on the simulation results transmission system client and server. Experiments will be conducted using thirty-text data, each of data will be measured on the performance of both encryption and authentication process between the previous method and proposed method. Experimental results show the performance of the proposed method has better speed to process application for security of data transmission systems, with performance to authenticate approximately 5 ms from the client side and server side.

Faster Data Forwarding in Content-Centric Network via Overlaid Packet Authentication Architecture

Content-Centric Networking (CCN) is one of the emerging paradigms for the future Internet, which shifts the communication paradigm from host-centric to data-centric. In CCN, contents are delivered by their unique names, and a public-key-based signature is built into data packets to verify the authenticity and integrity of the contents. To date, research has tried to accelerate the validation of the given data packets, but existing techniques were designed to improve the performance of content verification from the requester’s viewpoint. However, we need to efficiently verify the validity of data packets in each forwarding engine, since the transmission of invalid packets influences not only security but also performance, which can lead to a DDoS (Distributed Denial of Service) attack on CCN. For example, an adversary can inject a number of meaningless packets into CCN to consume the forwarding engines’ cache and network bandwidth. In this paper, a novel authentication architecture is introduced, which can support faster forwarding by accelerating the performance of data validation in forwarding engines. Since all forwarding engines verify data packets, our authentication architecture can eliminate invalid packets before they are injected into other CCN nodes. The architecture utilizes public-key based authentication algorithms to support public verifiability and non-repudiation, but a novel technique is proposed in this paper to reduce the overhead from using PKI for verifying public keys used by forwarding engines and end-users in the architecture. The main merit of this work is in improving the performance of data-forwarding in CCN regardless of the underlying public-key validation mechanism, such as PKI, by reducing the number of accesses to the mechanism. Differently from existing approaches that forgive some useful features of the Naive CCN for higher performance, the proposed technique is the only architecture which can support all useful features given by the Naive CCN.

Message authentication algorithm for OFDM communication systems

With the huge expansion in the telecommunications industry, the need for robust information security is becoming more critical than ever. Physical Layer Security has, recently, emerged as a promising candidate to secure emerging communication systems in a lightweight manner. This approach has proven to be superior to existing schemes, which has motivated many researchers to shift their work towards studying, understanding and exploiting the randomness of the physical layer. In this context, this paper presents a novel keyed-hash function for Orthogonal Frequency Division Multiplexing (OFDM) systems based on the physical characteristics and properties of wireless channels. More specifically, communicating entities sharing the same channel, extract common properties and mix them with a pre-shared secret key to produce a channel-based dynamic key. This key will later be used to generate the cipher primitives needed for performing source authentication and message integrity of the transmitted OFDM symbols. Since OFDM symbols, in the frequency-domain and time-domain, have different properties, the proposed keyed-hash function is modified and adapted to suit each case leading to two variants of the solution. To the best of our knowledge, this is the first work that proposes a keyed-hash function for complex OFDM symbols, based on physical layer conditions. Finally, different security and performance tests are conducted to prove the robustness and efficiency of this technique, in comparison to currently employed message authentication schemes.

An Image Hashing Algorithm for Authentication with Multi-Attack Reference Generation and Adaptive Thresholding

Image hashing-based authentication methods have been widely studied with continuous advancements owing to the speed and memory efficiency. However, reference hash generation and threshold setting, which are used for similarity measures between original images and corresponding distorted version, are important but less considered by most of existing models. In this paper, we propose an image hashing method based on multi-attack reference generation and adaptive thresholding for image authentication. We propose to build the prior information set based on the help of multiple virtual prior attacks, and present a multi-attack reference generation method based on hashing clusters. The perceptual hashing algorithm was applied to the reference/queried image to obtain the hashing codes for authentication. Furthermore, we introduce the concept of adaptive thresholding to account for variations in hashing distance. Extensive experiments on benchmark datasets have validated the effectiveness of our proposed method.

Blockchain-Based Internet of Vehicles Privacy Protection System

With the development of wireless local area networks and intelligent transportation technologies, the Internet of Vehicles is considered to be an effective method to alleviate the severe situation of the current transportation system. The vehicles in the Internet of Vehicles system build the Vehicular Ad Hoc Networks through wireless communication technology and dynamically provide different services through the real-time driving information broadcast by the vehicles. Vehicle drivers can control the distance, planning the driving route, between vehicles according to the current traffic environment, which improves the overall safety and efficiency of the traffic system. Due to the particularity of the Internet of Vehicles system service, vehicles need to broadcast their location information frequently. Attackers can collect and analyze vehicle broadcast information to steal privacy and even directionally track the owner through the driving trajectory, bringing serious security risks. This paper proposes a blockchain-based privacy protection system for the Internet of Vehicles. The system combines the blockchain with the Internet of Vehicles system to design a safe and efficient two-way authentication and key agreement algorithm through encryption and signature algorithm, which also solves the central dependency problem of the traditional Internet of Vehicles system.

Model-Free Data Authentication for Cyber Security in Power Systems

With the development and wide deployment of measurement equipment, data can be automatically measured and visualized for situation awareness in power systems. However, the cyber security of power systems is also threated by data spoofing attacks. This letter proposed a measurement data source authentication (MDSA) algorithm based on feature extraction techniques including ensemble empirical mode decomposition (EEMD) and fast Fourier transform (FFT), and machine learning for real-time measurement data classification. Compared with previous work, the proposed algorithm can achieve higher accuracy of MDSA using a shorter window of data from closely located synchrophasor measurement sensors.

Inner Knuckle Print Identification Using Artificial Neural Network

A inner knuckle print identification system has been designed and developed. This work presents a new approach to authenticate people according to their finger textures. This proposed method consists of three stages. They are preprocessing, feature extraction and matching. In the first stage, noise is suppressed using an image filtering. In the second stage, features are extracted by local line binary pattern. Artificial neural network and support vector machine are used to provide an efficient matching algorithm for inner knuckle print authentication. After matching, the algorithm returns the best match for the given fingerprint parameters. The use of inner knuckle print in biometric identification has been the most widely used authentication system. A classification with an accuracy of 89% and 97% has been obtained by support vector machine and artificial neural network classifier.

Fuzzy Learning for Multi-Dimensional Adaptive Physical Layer Authentication: A Compact and Robust Approach

The performance of physical layer authentication schemes strongly suffers from the uncertainties and dynamics of communications, which are mainly caused by the time-varying channels with unpredictable interference conditions. In this paper, we propose a multi-dimensional adaptive physical layer authentication scheme to achieve reliable authentication performance in time-varying environments. First of all, the fuzzy theory is explored for modeling multiple physical layer attributes with imperfectness and uncertainties. The designed fuzzy theory-based model is a parametric method that requires less observed samples of the utilized attributes together with less authentication system parameters to be determined compared with the nonparametric methods, demonstrating a compact authentication model. By deriving the false alarm rate and misdetection rate of the designed model, a hybrid learning-based adaptive authentication algorithm is proposed to near-instantaneously update system parameters, thereafter to adapt to the time-varying environment. Hence, our scheme is applicable to the communication environment with uncertainties and dynamics, resulting in a robust authentication scheme. Simulation results show that our solution can significantly improve the authentication performance in the time-varying environment. Compared with some exiting schemes, i.e., the optimal weights-based scheme and neural network-based scheme, our scheme achieves much better authentication performance.

A Novel Optimal Routing Protocol for Wireless Ad hoc Network with the aid of Double Encryption Mechanism

Ad hoc network paved way to various researches and application due to its wide acceptance over wired network. The advance has also led to various drawbacks or problems that can result in unauthorized usage of data or in data loss. So secured data transfer has become an important requirement in any Ad hoc network. Various issues exist in Ad hoc network while data transmission and hence it has become a major requirement to develop an efficient routing protocol that can transmit the data securely over the network. So, this paper provides a solution, intend to develop an approach for making the data transmission more secured and feasible. This paper incorporates double encryption scheme to secure the data where we use Hybrid DNA based cryptosystem and blow fish algorithm for authentication of users. Also, we design an efficient optimal routing protocol that makes the transmission secured by reducing various attacks that occur in the network. It provides the security for image transmission over internet effectively. This technique also can be extended in multimedia security over the internet. The network parameters will be approximately judged in order to demonstrate the performance of the scheme we develop.

Improving the quality of the technological process of packaging shape formation based on the information structure of an automated system

Based on the information structure of an automated quality monitoring system, we have designed a system to analyze information on the quality of forming the shape of PET-packaging, with a possibility of statistical control over the technological process using Shewhart control charts. That has been demonstrated using an example of the proposed technique of quality estimation of the finished PET bottles based on the thickness of their walls. Obtaining high-quality PET-packaging directly depends on the degree of perfection of all technological stages, thereby predetermining the necessity to build an effective system to control and manage the technological process of the shape formation of bottles made from polyethylene terephthalate. An analysis of information about the quality of PET-packaging shape formation based on monitoring the information structure of an automated system would make it possible to ensure operative adjustment of shape forming parameters at the minimized percentage of defects by organizing selective control over the products made. The use of statistical methods based on Shewhart control charts could enable the development of authentic algorithms for monitoring the shape formation quality aimed to track violations of technological parameters and compile recommendations on improving the process quality, as well as resource-use efficiency. The statistical estimation of cause-effect relations between the main technological parameters and product quality indicators involves the algorithm that monitors the quality of PET-packaging shape formation. This makes it possible to ensure the minimum level of defects in bottles when applying the devised Shewhart control chart. We have proposed a fuzzy cognitive chart for defining the preventive corrective actions directed at the elimination of the main causes of a defect at bottle shape formation, taking into consideration the interrelations of factors and their consequences on the resulting process quality