Biblio

In this paper, an implementation of a human in the loop (HITL) technique for robot navigation in an indoor environment is described. The HITL technique is integrated into the reinforcement learning algorithms for mobile robot navigation. Reinforcement algorithms, specifically Q-learning and SARSA, are used combined with HITL since these algorithms are good in exploration and navigation. Turtlebot3 has been used as the robot for validating the algorithms by implementing the system using Robot Operating System and Gazebo. The robot-assisted with human feedback was found to be better in navigation task execution when compared to standard algorithms without using human in the loop. This is a work in progress and the next step of this research is exploring other reinforced learning methods and implementing them on a physical robot.

The Internet obviously has a major impact on the global economy and human life every day. This boundless use pushes the attack programmers to attack the data frameworks on the Internet. Web attacks influence the reliability of the Internet and its administrations. These attacks are classified as User-to-Root (U2R), Remote-to-Local (R2L), Denial-of-Service (DoS) and Probing (Probe). Subsequently, making sure about web framework security and protecting data are pivotal. The conventional layers of safeguards like antivirus scanners, firewalls and proxies, which are applied to treat the security weaknesses are insufficient. So, Intrusion Detection Systems (IDSs) are utilized to screen PC and data frameworks for security shortcomings. IDS adds more effectiveness in securing networks against attacks. This paper presents an IDS model based on Deep Learning (DL) with Convolutional Neural Network (CNN) hypothesis. The model has been evaluated on the NSLKDD dataset. It has been trained by Kddtrain+ and tested twice, once using kddtrain+ and the other using kddtest+. The achieved test accuracies are 99.7% and 98.43% with 0.002 and 0.02 wrong alert rates for the two test scenarios, respectively.

Currently, most companies systematically face challenges related to the loss of significant confidential information, including legally significant information, such as personal data of customers. To solve the problem of maintaining the confidentiality, integrity and availability of information, companies are increasingly using the methodology laid down in the basis of the international standard ISO / IEC 27001. Information security risk management is a process of continuous monitoring and systematic analysis of the internal and external environment of the IT environment, associated with the further adoption and implementation of management decisions aimed at reducing the likelihood of an unfavorable result and minimizing possible threats to business caused by the loss of manageability of information that is important for the organization. The article considers the problems and approaches to the development, practical implementation, and methodology of risk management based on the international standard ISO 31000 in the modern information security management system.

The digitalization of safety-critical railroad infrastructure enables new types of attacks. This increases the need to integrate Information Technology (IT) security measures into railroad systems. For that purpose, we rely on a security architecture for a railway object controller which controls field elements that we developed in previous work. Our architecture enables the integration of security mechanisms into a safety-certified railway system. In this paper, we demonstrate the practical feasibility of our architecture by using a Trusted Platform Module (TPM) 2.0 and a Multiple Independent Levels of Safety and Security (MILS) Separation Kernel (SK) for our implementation. Our evaluation includes a test bed and shows how certification and homologation can be achieved.

Relational database management systems not only support larger-than-memory data processing and very advanced query optimization, but also offer the benefits of data security, privacy, and consistency. When machine learning on large data sets is processed directly on an existing SQL database server, the data does not need to be exported and transferred to a separate big data processing platform. To achieve this, we implement a linear regression algorithm using SQL code generation such that the computation can be performed server-side and directly in the RDBMs. Our method and its implementation, programmed in Python, solves linear regression (LR) using the ordinary least squares (OLS) method directly in the RDBMS using SQL code generation, leaving most of the processing in the database. Only the matrix of the system of equations, whose size is equal to the number of variables squared, is transferred from the SQL server to the Python client to be solved for OLS regression. For evaluation purposes, our LR implementation was tested with artificially generated datasets and compared to an existing Python library (Scikit Learn). We found that our implementation consistently solves OLS regression faster than Scikit Learn for datasets with more than 10,000 input rows, and if the number of columns is less than 64. Moreover, under the same test conditions where the computation is larger than memory, our implementation showed a fast result, while Scikit returned an out-of-memory error. We conclude that SQL is a promising tool for in-database processing of large-volume, low-dimensional data sets with a particular class of machine learning algorithms, namely those that can be efficiently solved with map-reduce queries such as OLS regression.

Signcryption is a sophisticated cryptographic tool that combines the benefits of digital signature and data encryption in a single step, resulting in reduced computation and storage cost. However, the existing signcryption techniques do not account for a scenario in which a company must escrow an employee's private encryption key so that the corporation does not lose the capacity to decrypt a ciphertext when the employee or user is no longer available. To circumvent the issue of non-repudiation, the private signing key does not need to be escrowed. As a result, this paper presents an implicit certificate-based signcryption technique with private encryption key escrow, which can assist an organization in preventing the loss of private encryption. A certificate, or more broadly, a digital signature, protects users' public encryption and signature keys from man-in-the-middle attacks under our proposed approach.

Traditional grid-centric data storage methods are vulnerable to network attacks or failures due to downtime, causing problems such as data loss or tampering. The security of data storage can be effectively improved by establishing an alliance chain. However, the existing consortium chain consensus algorithm has low scalability, and the consensus time will explode as the number of nodes increases. This paper proposes an improved consensus algorithm (MSBFT) based on multi-signature to address this problem, which spreads data by establishing a system communication tree, reducing communication and network transmission costs, and improving system scalability. By generating schnorr multi-signature as the shared signature of system nodes, the computational cost of verification between nodes is reduced. At the end of the article, simulations prove the superiority of the proposed method.

In recent years, hashing algorithm has been widely researched and has made considerable progress in large-scale image retrieval tasks due to its advantages of convenient storage and fast calculation efficiency. Nowadays most researchers use deep convolutional neural networks (CNNs) to perform feature learning and hash coding learning at the same time for image retrieval and the deep hashing methods based on deep CNNs perform much better than the traditional manual feature hashing methods. But most methods are designed to handle simple binary similarity and decrease quantization error, ignoring that the features of similar images and hashing codes generated are not compact enough. In order to enhance the performance of CNNs-based hashing algorithms for large scale image retrieval, this paper proposes a new deep-supervised hashing algorithm in which a novel channel attention mechanism is added and the loss function is elaborately redesigned to generate compact binary codes. It experimentally proves that, compared with the existing hashing methods, this method has better performance on two large scale image datasets CIFAR-10 and NUS-WIDE.

Adaptive feedback cancellation (AFC) method is widely adopted for the purpose of reducing the adverse effects of acoustic feedback on the sound reinforcement systems. However, since the existence of forward path results in the correlation between the source signal and the feedback signal, the source signal is mistakenly considered as the feedback signal to be eliminated by adaptive filter when it is colored, which leads to a inaccurate prediction of the acoustic feedback signal. In order to solve this problem, prediction error method is introduced in this paper to remove the correlation between the source signal and the feedback signal. Aiming at the dilemma of Modified Least Mean Square (MLMS) algorithm in choosing between prediction speed and prediction accuracy, an improved MLMS algorithm with a variable step-size scheme is proposed. Simulation examples are applied to show that the proposed algorithm can obtain more accurate prediction of acoustic feedback signal in a shorter time than the MLMS algorithm.

Despite the recent introduction of biometric identification technology, Personal Identification Numbers (PIN) are the standard for granting access to restricted areas and for authorizing operations on most systems, including mobile phones, payment devices, smart locks. Unfortunately, PINs have several inherent vulnerabilities and expose users to different types of social engineering attacks. Specifically, the risk of shoulder surfing in PIN-based authentication is especially high for individuals who are blind. In this paper, we introduce a new method for improving the trade-off between security and accessibility in PIN-based authentication systems. Our proposed solution aims at minimizing the threats posed by malicious agents while maintaining a low level of complexity for the user. We present the method and discuss the results of an evaluation study that demonstrates the advantages of our solution compared to state-of-the-art systems.

Machine learning algorithms are becoming more and more widespread in industrial as well as in societal settings. This diffusion is starting to become a critical aspect of new software-intensive applications due to the need of fast reactions to changes, even if temporary, in data. This paper investigates on the improvement of reliability in the Machine Learning based classification by extending Random Forests with Bayesian Network models. Such models, combined with a mechanism able to adjust the reputation level of single learners, may improve the overall classification trustworthiness. A small example taken from the healthcare domain is presented to demonstrate the proposed approach.

Generalizing automated medical image segmentation methods to new image domains is inherently difficult. We have previously developed a number of automated segmentation methods that perform at the level of human readers on images acquired under similar conditions to the original training data. We are interested in exploring techniques that will improve model generalization to new imaging domains. In this study we explore a method to limit the inherent bias of these models to intensity and textural information. Using a dataset of 100 T2-weighted MR images with fat-saturation, and 100 T2-weighted MR images without fat-saturation, we explore the use of neural style transfer to induce shape preference and improve model performance on the task of segmenting the kidneys in patients affected by polycystic kidney disease. We find that using neural style transfer images improves the average dice value by 0.2. In addition, visualizing individual network kernel responses highlights a drastic difference in the optimized networks. Biasing models to invoke shape preference is a promising approach to create methods that are more closely aligned with human perception.

In recent times, the world has seen a tremendous increase in the number of attacks on IoT devices. A majority of these attacks have been botnet attacks, where an army of compromised IoT devices is used to launch DDoS attacks on targeted systems. In this paper, we study how the choice of a dataset and the extracted features determine the performance of a Machine Learning model, given the task of classifying Linux Binaries (ELFs) as being benign or malicious. Our work focuses on Linux systems since embedded Linux is the more popular choice for building today’s IoT devices and systems. We propose using 4 different types of files as the dataset for any ML model. These include system files, IoT application files, IoT botnet files and general malware files. Further, we propose using static, dynamic as well as network features to do the classification task. We show that existing methods leave out one or the other features, or file types and hence, our model outperforms them in terms of accuracy in detecting these files. While enhancing the dataset adds to the robustness of a model, utilizing all 3 types of features decreases the false positive and false negative rates non-trivially. We employ an exhaustive scenario based method for evaluating a ML model and show the importance of including each of the proposed files in a dataset. We also analyze the features and try to explain their importance for a model, using observed trends in different benign and malicious files. We perform feature extraction using the open source Limon sandbox, which prior to this work has been tested only on Ubuntu 14. We installed and configured it for Ubuntu 18, the documentation of which has been shared on Github.

In today’s world, Supervisory Control and Data Acquisition (SCADA) networks have many critical tasks, including managing infrastructure such as power, water, and sewage systems, and controlling automated manufacturing and transportation systems. Securing these systems is crucial. Here we describe a project to design security into an example system using formal specifications. Our example system is a component in a cybersecurity testbed at the University of Cincinnati, which was described in previous work. We also show how a design flaw can be discovered and corrected early in the system development process.

Various algorithms and models have been proposed to address text classification tasks; however, they rarely consider incorporating the additional knowledge hidden in class labels. We argue that hidden information in class labels leads to better classification accuracy. In this study, instead of encoding the labels into numerical values, we incorporated the knowledge in the labels into the original model without changing the model architecture. We combined the output of an original classification model with the relatedness calculated based on the embeddings of a sequence and a keyword set. A keyword set is a word set to represent knowledge in the labels. Usually, it is generated from the classes while it could also be customized by the users. The experimental results show that our proposed method achieved statistically significant improvements in text classification tasks. The source code and experimental details of this study can be found on Github11https://github.com/HeroadZ/KiL.

In-browser cryptomining uses the computational power of a website's visitors to mine cryptocurrency, i.e., to create new coins. With the rise of ready-to-use mining scripts distributed by service providers (e.g., Coinhive), it has become trivial to turn a website into a cryptominer by copying and pasting the mining script. Both legitimate webpage owners who want to raise an extra revenue under users' explicit consent and malicious actors who wish to exploit the computational power of the users' computers without their consent have started to utilize this emerging paradigm of cryptocurrency operations. In-browser cryptomining, though mostly abused by malicious actors in practice, is indeed a promising funding model that can be utilized by website owners, publishers, or non-profit organizations for legitimate business purposes, such as to collect revenue or donations for humanitarian projects, inter alia. However, our analysis in this paper shows that in practice, regardless of their being legitimate or not, all in-browser mining scripts are treated the same as malicious cryptomining samples (aka cryptojacking) and blacklisted by browser extensions or antivirus programs. Indeed, there is a need for a better understanding of the in-browser cryptomining ecosystem. Hence, in this paper, we present an in-depth empirical analysis of in-browser cryptomining processes, focusing on the samples explicitly asking for user consent, which we call permissioned cryptomining. To the best of our knowledge, this is the first study focusing on the permissioned cryptomining samples. For this, we created a dataset of 6269 unique web sites containing cryptomining scripts in their source codes to characterize the in-browser cryptomining ecosystem by differentiating permissioned and permissionless cryptomining samples. We believe that (1) this paper is the first attempt showing that permissioned in-browser cryptomining could be a legitimate and viable monetization tool if implemented responsibly and without interrupting the user, and (2) this paper will catalyze the widespread adoption of legitimate crvptominina with user consent and awareness.

With China's overall national strength, the education of studying in China has entered a period of rapid development, and China has become one of the important destination countries for international student mobility. With political stability, rapid economic development, and continuous improvement in the quality of higher education, the educational value of studying in China is increasingly recognized by international students. International students study and live in the same way as domestic students. While the development of the Internet has brought convenience to people, it has also created many security risks. How to protect the information security of international students is the focus of this paper. This paper introduces the classification, characteristics and security risks of international students' personal information. In order to protect the private data of international students from being leaked, filtering rules are set in the campus network through WinRoute firewall to effectively prevent information from being leaked, tampered or deleted, which can be used for reference by other universities.

The Government of Indonesia has implemented an Electronic-Based Government System (SPBE) to provide fast and unlimited services by distance, space, and time. The Case Investigation Information System (SIPP) is a service for the public that requires good integration of information so that legal services are provided quickly and easily. In 2020 court websites experienced many hacker attacks based on data from internal court sources, at least there were more than 20 courts throughout Indonesia that were affected by damage to both the website, the SIPP web feature, and the court library featured. Based on the Minister of Communication and Informatics Regulation No. 4 of 2016 in article 7, every SPBE organizer must implement information security following the information security standards described by the Ministry of Communication and Information. Since this regulation is conceived to minimize the risk of the security breach on SPBE, and there is such numerous security breach in 2020 therefore this indicates poorly implemented of the regulation. Based on this finding this research aims to investigate which area is neglected. To achieve this, this research employs gap analysis using ISO/IEC 27001:2013and maturity level to reveal the neglected areas in information security. Current findings show there are SIPP users that still use weak passwords and lack of awareness of top management personnel in several information security areas such as securing sensitive documents or policies that regulate information security specifically for SIPP. These findings entails that the security management in Court is most likely at the initiative level.

This research covers the problem related to user behavior and its relationship with the protection of computer assets in terms of confidentiality, integrity, and availability. The main objective was to evaluate the relationship between the dimensions of awareness, compliance and appropriation of the information security culture and the asset protection variable, the ISCA diagnostic instrument was applied, and social engineering techniques were incorporated for this process. The results show the levels of awareness, compliance and appropriation of the university that was considered as a case study, these oscillate between the second and third level of four levels. Similarly, the performance regarding asset protection ranges from low to medium. It was concluded that there is a significant relationship between the variables of the investigation, verifying that of the total types of incidents registered in the study case, approximately 69% are associated with human behavior. As a contribution, an information security culture model was formulated whose main characteristic is a complementary diagnostic process between surveys and social engineering techniques, the model also includes the information security management system, risk management and security incident handling as part of the information security culture ecosystem in an enterprise.

In order to solve the problem of quantitative assessment of information security risks in industrial control systems, this paper proposes a method of information security risk assessment for industrial control systems based on modular hybrid genetic algorithm. Combining with the characteristics of industrial control systems, the use of hybrid genetic algorithm evidence theory to identify, evaluate and assess assets and threats, and ultimately come to the order of the size of the impact of security threats on the specific industrial control system information security. This method can provide basis for making decisions to reduce information security risks in the control system from qualitative and quantitative aspects.

Cloud computing is a modern computing mode based on network, which is widely participated by the public, and provides virtualized dynamic computing resources in the form of services. Cloud computing builds an effective communication platform with the help of computer internet, so that users can get the same computing resources even if they are in different areas. With its unique technical characteristics and advantages, cloud computing has been deployed to practical applications more and more, and the consequent security problems of cloud computing have become increasingly prominent. In addition to the original cloud computing environment, this paper proposes to build a secure cloud with cloud technology, deploy security agents in the business cloud, connect the business cloud, security cloud and security agents through SDN (software defined network) technology, and dynamically divide the business cloud into logically isolated business areas through security agents. Therefore, security is separated from the specific implementation technology and deployment scheme of business cloud, and an information security protection scheme under cloud computing environment is proposed according to the characteristics of various factors, so as to enhance the security of network information.

Recommender systems help people in finding a particular item based on their preference from a wide range of products in online shopping rapidly. One of the most popular models of recommendation systems is the Collaborative Filtering Recommendation System (CFRS) that recommend the top-K items to active user based on peer grouping user ratings. The implementation of CFRS is easy and it can easily be attacked by fake users and affect the recommendation. Fake users create a fake profile to attack the RS and change the output of it. Different attack types with different features and attacking methods exist in which decrease the accuracy. It is important to detect fake users, remove their rating from rating matrix and recognize the items has been attacked. In the recent years, many algorithms have been proposed to detect the attackers but first, researchers have to inject the attack type into their dataset and then evaluate their proposed approach. The purpose of this article is to develop a tool to inject the different attack types to datasets. Proposed tool constructs a new dataset containing the fake users therefore researchers can use it for evaluating their proposed attack detection methods. Researchers could choose the attack type and the size of attack with a user interface of our proposed tool easily.

Nearest neighbor (NN) search is an essential operation in many applications, such as one/few-shot learning and image classification. As such, fast and low-energy hardware support for accurate NN search is highly desirable. Ternary content-addressable memories (TCAMs) have been proposed to accelerate NN search for few-shot learning tasks by implementing \$L\$∞ and Hamming distance metrics, but they cannot achieve software-comparable accuracies. This paper proposes a novel distance function that can be natively evaluated with multi-bit content-addressable memories (MCAMs) based on ferroelectric FETs (Fe-FETs) to perform a single-step, in-memory NN search. Moreover, this approach achieves accuracies comparable to floating-point precision implementations in software for NN classification and one/few-shot learning tasks. As an example, the proposed method achieves a 98.34% accuracy for a 5-way, 5-shot classification task for the Omniglot dataset (only 0.8% lower than software-based implementations) with a 3-bit MCAM. This represents a 13% accuracy improvement over state-of-the-art TCAM-based implementations at iso-energy and iso-delay. The presented distance function is resilient to the effects of FeFET device-to-device variations. Furthermore, this work experimentally demonstrates a 2-bit implementation of FeFET MCAM using AND arrays from GLOBALFOUNDRIES to further validate proof of concept.

IoT applications are changing our daily lives. These innovative applications are supported by new communication technologies and protocols. Particularly, the information-centric network (ICN) paradigm is well suited for many IoT application scenarios that involve large-scale wireless sensor networks (WSNs). Even though the ICN approach can significantly reduce the network traffic by optimizing the process of information recovery from network nodes, it is also possible to apply data aggregation strategies. This paper proposes an unsupervised machine learning-based data aggregation strategy for multi-hop information-centric WSNs. The results show that the proposed algorithm can significantly reduce the ICN data traffic while having reduced information degradation.

This paper presents a design concept of an innovative CAPTCHA that can filter the color-vision–recognition states of different users. It can simultaneously verify the real-human-user identity, differentiate between the color-vision needs, and decide the content to be presented automatically.