University of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701Vol.8, No. 2, 20211862638810.22108/jcs.2021.26388ENJournal Article20220226Volume 8, Issue 2, Summer and Autumn 2021, Pages 1-86https://jcomsec.ui.ac.ir/article_26388_2f4b1a16e28f934c8aec2d58dda14ccb.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701BAS: An Answer Selection Method Using BERT Language Model1182603710.22108/jcs.2021.128002.1066ENJamshidMozafariFaculty of Computer Engineering, University of Isfahan, Isfahan, Iran.AfsanehFatemiFaculty of Computer Engineering, University of Isfahan, Isfahan, Iran.Mohammad AliNematbakhshFaculty of Computer Engineering, University of Isfahan, Isfahan, Iran.Journal Article20210405In recent years, Question Answering systems have become more popular and widely used by users. Despite the increasing popularity of these systems, their performance is not even sufficient for textual data and requires further research. These systems consist of several parts that one of them is the Answer Selection component. This component detects the most relevant answer from a list of candidate answers. The methods presented in previous researches have attempted to provide an independent model to undertake the answer-selection task. An independent model cannot comprehend the syntactic and semantic features of questions and answers with a small training dataset. To fill this gap, language models can be employed in implementing the answer selection part. This action enables the model to have a better understanding of the language in order to understand questions and answers better than previous works. In this research, we will present the 'BAS' stands for BERT Answer Selection that uses the BERT language model to comprehend language. The empirical results of applying the model on the TrecQA Raw, TrecQA Clean, and WikiQA datasets demonstrate that using a robust language model such as BERT can enhance the performance. Using a more robust classifier also enhances the effect of the language model on the answer selection component. The results demonstrate that language comprehension is an essential requirement in natural language processing tasks such as answer selection.https://jcomsec.ui.ac.ir/article_26037_94f3880c9298615831ab4f3fbb6da3f5.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701Indoor Path Tracking Using Combination of Viterbi and WKNN19262608710.22108/jcs.2021.129843.1078ENFatemehAli Asgari RenaniComputer Engineering Group, Faculty of Engineering, Arak University, Sardasht, Arak, Iran.HosseinGhaffarianComputer Engineering Group, Faculty of Engineering, Arak University, Sardasht, Arak, Iran.MastanehChegeniComputer Engineering Group, Faculty of Engineering, Arak University, Sardasht, Arak, Iran.Journal Article20210802In this paper, we focus to find desired node position in indoor environments using a sequence of observations and user movement records. For this purpose, we first record the user's movements in indoor environments by defining a set of states and several matrices, which are Viterbi inputs. To record the fingerprints of the environment, we move across the entire coordinates of the building to collect and record the fingerprints of different places. In the online phase, we use the Weighted K-Nearest Neighbors (WKNN) algorithm in parallel to check the accuracy of both WKNN and Viterbi algorithms and to correct the WKNN behavior by Viterbi. During this phase, an experimental node is inserted into the environment and moves in the desired direction by determining the destination. The proposed method calculates the current location of the node and its most probable location in the next step. The results of the implementation and testing of the proposed algorithm in the Faculty of Engineering, Arak University, show the optimal performance of the proposed idea for predicting the location and path of the node.https://jcomsec.ui.ac.ir/article_26087_9806e9bf7a0931830cf828bf7e8aba19.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701Intrusion Detection in IoT With Logistic Regression and Artificial Neural Network: Further Investigations on N-BaIoT Dataset Devices27422621210.22108/jcs.2021.129807.1077ENFereshtehAbbasiDepartment of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.MarjanNaderanDepartment of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.Seyyed EnayatallahAlaviDepartment of Computer Engineering, Shahid Chamran University of Ahvaz, Ahvaz, Iran.Journal Article20210827Due to the increasing development and applications of the Internet of Things (IoT), detection and prevention of intruders into the network and devices has gained much attention in the past decade. For this challenge, traditional solutions of Intrusion Detection Systems (IDS) are not responsive in IoT environments or at least may not be very efficient. In this article, we deeply investigate the previous methods of using machine learning methods for intrusion detection in IoT, and two methods for feature extraction and classification are proposed. The first method is feature extraction and classification using Logistic Regression (LR) and the second method is to use an Artificial Neural Network (ANN) for classification. To evaluate the performance of the proposed method, six devices of the N_BaIoT dataset, which consists of data samples related to nine devices IoT and several attacks are used according to some criteria for evaluating the performance of the proposed methods. Simulation results in comparison with some other deep learning methods in terms of accuracy, precision, recall and F1-score show that using logistic regression, is more efficient and above 90% classification accuracy is achieved.https://jcomsec.ui.ac.ir/article_26212_c9062f99f53e6f12d7a5e124b59b0cfe.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701Scalability Analysis of a LoRa Network Under Inter-SF and Co-SF Interference with Poisson Point Process Model43572626110.22108/jcs.2021.129691.1073ENSolmazMohammadiDepartment of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology (IROST), Tehran, Iran.GholamrezaFarahaniDepartment of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology (IROST), Tehran, Iran.Journal Article20210810The scalability of a single gateway LoRa network depends on different parameters such as interference and noise. The scheme of spreading factor allocation can control the interference and noise. This article analyzes the impact of the interference of the concurrent transmission with the same spreading factor (co-SF) and different spreading factor (inter-SF) on the scalability of the LoRa network. The interference has been modeled as the Poisson point process. The proposed scheme considers the success probabilities and device density (SPD) in each area in determining the width and boundaries of SF areas. The simulation results showed that the proposed SPD scheme had improved 13.20% over the EIB method in terms of success probability under joint co-SF and inter-SF interference. Also, the coverage probability under the joint impact of cumulative co-SF and inter-SF interference of the SPD and EIB methods is compared in the clean and noisy conditions. The probability of coverage in EIB degrades more than SPD as the scalability increases. Also, the uplink performance of the proposed SPD scheme has been studied in the absence of any interference under AWGN. SPD has a higher success probability under AWGN than EIB.<br /> https://jcomsec.ui.ac.ir/article_26261_f0372078803ac1f63b635792784cb0bf.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701Analyzing the Impact of Wireless Channels on the Efficiency of Edge Computing in IoT Applications59702628610.22108/jcs.2021.129685.1072ENGhazalJabbariFaculty of Engineering, Shahrekord University, Shahrekord, Iran.AliGhiasianFaculty of Engineering, Shahrekord University, Shahrekord, Iran.Journal Article20210725The Internet of Things (IoT) has provided a platform for different devices to interact extensively over the Internet. This technology produces a large amount of data that needs to be stored and processed in devices. On the other hand, hardware constraints on IoT devices pose a major challenge to energy consumption and latency. Edge Computing (EC) has brought many benefits as a promising solution to increase the computing and storage capacity of internet-connected devices. It is expected that EC helps IoT to reduce energy consumption and computational delay of devices. However, the conditions of the wireless channel and specifically the possibility of errors in data transmission over wireless links could have an adverse impact on the performance of the whole system. In this paper, by performing calculations in both local and edge environments and by considering the retransmission of data to eliminate possible errors, the role of wireless channels in the efficiency of offloading to the EC is investigated. The results show that offloading the calculations to EC does not always reduce energy consumption and delay. Therefore, the conditions of the wireless channel should be considered for an appropriate decision regarding the offloading of tasks to the EC or its execution in IoT devices.https://jcomsec.ui.ac.ir/article_26286_8beea2ab7ee008ba524f0fbf3dfd0f6c.pdfUniversity of Isfahan & Iranian Society of CryptologyJournal of Computing and Security2322-44608220210701A Lightweight Authentication Scheme for RFID with Permutation Operation on Passive Tags71862636810.22108/jcs.2022.129023.1068ENAlirezaAbdellahi KhorasganiDepartment of Electrical Engineering, Khorasgan (Isfahan) Branch, Islamic Azad University, Isfahan, Iran.MahdiSadjadiehDepartment of Electrical Engineering, Khorasgan (Isfahan) Branch, Islamic Azad University, Isfahan, Iran.Mohammad RohollahYazdaniDepartment of Electrical Engineering, Khorasgan (Isfahan) Branch, Islamic Azad University, Isfahan, Iran.Journal Article20210623Rapid and ever-increasing Internet of things (IoT) developments have brought about great hopes of improving the quality of human life. Radio-frequency identification (RFID) employed as a backup technology in the IoT is widely used in different aspects of life. Therefore, high priority should be given to security problems and user privacy protection. However, limited computational power and storage resources in passive tags have made the implementation of security measures difficult in RFID. In other words, the design of lightweight authentication protocols for RFID systems is still a major challenge in RFID security. A lightweight authentication protocol has been recently proposed for passive tags by Liu et al. Using specific inverse operations in the IOLAS protocol, they claimed that the lightweight bitwise operations would make this protocol resistant against known and potential attacks in RFID systems. This study aimed to show that the same inverse operations pose the main problem so that this protocol fails to guarantee backward security. It was also indicated that the IOLAS protocol is vulnerable to replay, reader impersonation, tag tracking attacks, and secret disclosure attack. Finally, we improved the IOLAS protocol and proposed the POLAS protocol, which is resistant to the currently known attacks. We analyze the security level of the proposed protocols and prove the security of the proposed design using BAN (Burrows-Abadi-Needham) logic. We also formally confirmed the security of the proposal using the Scyther simulation tool. According to security analysis, we can observe that this protocol have a high level of security. A comparison of the performance of the POLAS protocol shows that this protocol is comparable to similar protocols in terms of computational costs, storage costs, and communication costs.https://jcomsec.ui.ac.ir/article_26368_ce68705683761e03b0e84140324ea5a3.pdf