|
|
|
 |
Search published articles |
 |
|
Showing 78 results for Type of Study: Research Article
Narges Salehpour, Mohammad Nazari Farokhi, Ebrahim Nazari Farokhi,
Volume 3, Issue 2 (3-2015)
Abstract
Abstract One of the most important issues in securing computer networks is an Intrusion Detection System. Intrusion detection systems are searching for malicious behavior, deviation normal patterns and attacks on computer networks are discovered. This system recognizes the type of traffic allowed for unauthorized traffic. Since the today's data mining techniques to intrusion detection in computer networks are used. In this research is provided, a method for designing an intrusion detection system based on machine learning. One of the features of neural networks and machine learning systems, training is based on the training data. In this research is used for detecting the intrusion of machine learning to learn the features of the theory of Rough property that has a higher correlation coefficient is used. To train and evaluate has used the proposed approach the KDD CUP 99 dataset. This study, the accuracy of our method compares with feature-based learning algorithm, neural network self and decision tree. The simulation results show that the proposed system has high accuracy and speed of detection based on rough theory is right
, ,
Volume 4, Issue 1 (9-2015)
Abstract
Mahdi Ahmadipari, Meysam Moradi,
Volume 4, Issue 1 (9-2015)
Abstract
In recent years, the use of Meta-heuristic algorithms on various problem taken into consideration. Meta-heuristic algorithms in solving various problem, different performance show. An Meta-heuristic algorithm to solve a particular problem may have better performance than other algorithms and poorer performance have in other issue. In this study the performance of Meta-heuristic algorithms for a specific problem that explore cryption key Vigenere encryption algorithm will be examined. And Meta-heuristic different algorithms performance in terms of accuracy and speed of convergence of the results will be cryptanalyzed and the best algorithm is selected
, ,
Volume 4, Issue 2 (3-2016)
Abstract
As social networking services are popular, the need for recognizing reliable people has become a main concern. So, trust plays an important role in social networks in order to recognizing trustworthy people. The purpose of this paper is to propose an approach to recognize trustworthy users and protect users from misused by untrustworthy users. In this paper, we suggest a method to measure trust value based on call log histories and QoS requirements. After that, we calculate error-hit, precision and recall. Also, the trust issue in social networks is pointed out and the new approach to evaluate the trust based on call log histories and QoS requirements is proposed. The results indicate that the proposed approach has better error-hit, precision and recall than the other four models (FIFO, combined, QoS-based and call log-based).
Mahtab Roozbahani, Meysam Moradi, Parvaneh Mansoori,
Volume 5, Issue 1 (9-2016)
Abstract
In mathematics and computer science an optimization problem, the problem is finding the best solution among all possible solutions. Given the importance of the knapsack in computer sciences, different algorithms are used to solve it. Knapsack problem is a combinational problem of selectivity and the purpose of solving the most benefit by taking the capacity is the tolerable knapsack. Since the knapsack is a problem of constrained maximization. In this study, a mathematical model in the form of a function unlimited minimization and designed for it, hen this model on Particle Swarm Optimization , Firefly Algorithm and Artificial Bee Colony has been implemented in MATLAB software environment, The results show that the artificial bee colony algorithm, the model is better than the other two algorithms .The advantage of this model is the objective function , because minimization and unlimited models , to implement with many Bio-Inspired algorithms.
Sayed Mohamamd Tabatabaei Parsa, Hassan Shakeri,
Volume 5, Issue 1 (9-2016)
Abstract
Wireless Sensor Networks (WSNs) are an ideal solution for miscellaneous applications of surveillance and control, such as traffic control, environmental monitoring, and battlefield surveillance. The wireless sensor nodes have limited memory and processing capability. The Sybil Attack is a serious threat in which a malicious node creates multiple fake identities in order to mislead the other sensor nodes. This attack can have influence on routing protocols and the operations like voting and data aggregation. In this paper, we present a dynamic and lightweight algorithm with a confidence-aware trust approach. The Algorithm uses the trust value of each sensor node to reduce the false alarm rates and detect indirect Sybil attacks in WSNs. The simulation results demonstrate that the average detection and wrong detection rates are 92% and 0.08% respectively.
Ali Hadipour, Dr Seyed Mahdi Sajadieh, Raheleh Moradafifi,
Volume 5, Issue 1 (9-2016)
Abstract
The stream ciphers are set of symmetric cipher algorithms that receive the secret message as a sequence of bits and process encrypted operation using complex function according to key, IV and XOR combination of a sequence of bits. One of the goals in the design of stream ciphers is to get minimum great period using one of the primary T-functions. Also using jump index in designing LFSRs lead to complexity of stream ciphers based on LFSR analysis. In this paper, tried with using of T-functions concepts and jump index, a novel method presented for primary functions design with great period.
Dr Mansoor Fateh, Samira Rajabloo, Elahe Alipour,
Volume 5, Issue 2 (3-2017)
Abstract
In this paper, the image steganography based on LSB and pixel classification is reviewed. Then, the method for steganography information in image is presented. This method based on LSB. Our purpose of this paper is to minimize the changes in cover image. At the first, the pixels of the image are selected to hiding the message; second complemented message will be hidden in LSB of selected pixels. In this paper, to solve some problems LSB method and minimize the changes, pixels categorized based on values of bits of second, third, fourth. In each category, ratio of changed pixels to unchanged pixels is calculated. If the ratio is greater than one, the LSB of that category are reversed and those changes reach at least. Mean Square Error and Peak Signal to Noise Ratio are two criterions to evaluate stego-image quality. PSNR and MSE of proposed method in comparison with simple LSB method, are respectively growth rate 0.13 percent and reduction rate 0.19 percent.
, ,
Volume 5, Issue 2 (3-2017)
Abstract
The Identity Management System (IDM) is a set of policies, rules, procedures, and systems that manage authentication, access control, and audit activity based on digital identity. In the Identity Management System, given the storage of user identity attributes in the identity provider, users will lose their physical and traditional control over their personal identity, and on the other hand, user attributes are subject to more attacks from The inside of the system and the external attackers. Therefore, to ensure user's privacy control is keeping awareness of the release of his / her identity information, So providing security mechanisms in the area of privacy is essential. The current mechanisms have failed to satisfy users confidence in maintaining the security and privacy associated with their identity information. The designs presented in this area will increase user intervention and involvement during system interactions , and the user must act as an interface role. The Problems of the proposed designs, the high computational burden on a part of the system. In this article, the process of improving privacy control and user awareness for solving problems has been investigated.
Kamaleddin Ghezavati, Alireza Nowroozi,
Volume 6, Issue 2 (3-2018)
Abstract
Online social networks (OSNs) is one of the most popular medium for communicating, sharing, and publishing a considerable amount of information. OSN popularity often faces the challenge of dealing with unwanted messages and hidden malicious purposes in it. Based on recent studies, social network users can easily expose their confidential details with others. Misuse of this information can cause damage in virtual and real world. In this paper, main categories attacks are given on social network online security and privacy in four categories classic, modern, hybrid and children special attacks and ways that can be used to protect against different types of attacks used OSN users is the social network operators, security companies, and researchers are provided. Finally, eight ways to prevent these threats is presented.
Sayed Mohammad Tabatabaei Parsa, Hassan Shakeri,
Volume 6, Issue 2 (3-2018)
Abstract
Wireless Sensor Networks (WSNs) gather the environmental information via some sensor nodes and send them after some simple processing functions if necessary. These nodes are constrained devices in terms of memory, processing capability, radio range, and energy. Due to the unattended deployment of sensor nodes and the nature of wireless communications, these networks are vulnerable to several attacks. Among these, the Sybil Attack is a serious threat in which a malicious node creates multiple fake identities in order to mislead the other sensor nodes. In this case, the malicious node can attract lots of traffic and disrupt routing protocols. In this paper, we present a confidence-aware trust model considering Time Factor to detect such attacks. In this model, we use the indirect trust, gained from the neighbors' recommendations, in order to detect the indirect Sybil attacks, in which a legal node is not directly associated with the Sybil node. The Algorithm has been implemented using MATLAB. The simulation results demonstrate significant preference of the proposed method in terms of detection accuracy and false alarm rates. The average rate of detection and false detection of the proposed model are 93% and 0.26%.
Hadi Golbaghi, Mojtaba Vahidi Asl, Alireza Khalilian,
Volume 7, Issue 1 (9-2018)
Abstract
Malware writers leverage several techniques for thwarting the detection method of antimalware software. An effective technique is applying obfuscation techniques to make metamorphic malware. Metamorphism modifies the code structure in a way that while retaining the behavior, the pattern and structure of the code is changed. Recently, researchers have proposed a new method for metamorphic malware detection that works based on static analysis of malware code. However, some obfuscation techniques exist that when applied, the efficacy of static analyzes is adversely affected. To overcome this issue, in this paper, we apply a dynamic analysis in addition to static analysis. The new method elicits some information from both static and dynamic analyzes, combines them, and uses the resultant information to learn a classifier. The obtained classifier is then used to detect a new instance of an existing family of metamorphic malwares. In fact, the combination of both static and dynamic information is intended to address the weaknesses of each individual analysis and leads to an overall better effectiveness. In order to evaluate the proposed method, experiments on 450 files including benign files and 5 families of metamorphic malwares, namely MPCGEN, G2, VLC, NGVCK, and MWOR, have been conducted. The experiments were performed in three cases: static analysis, dynamic analysis, and the combination of both. The results of comparison among three cases show that metamorphic malware detection is not reached to 100 percent precision via either static or dynamic analysis individually. However, using the combination of both static and dynamic information could have consistently led to detection with 100 percent precision, which have been measured using ROC metric.
Meysam Moradi, Mahdi Abbasi,
Volume 7, Issue 2 (3-2019)
Abstract
For many years, cryptanalysis has been considered as an attractive topic in jeopardizing the security and resistance of an encryption algorithm. The SDES encryption algorithm is a symmetric cryptography algorithm that performs a cryptographic operation using a crypt key. In the world of encryption, there are many search algorithms to cryptanalysis. In these researches, brute force attack algorithm has been used as a complete search algorithm, genetic algorithm as an evolutionary intelligence algorithm, and standard particle swarm as an optimization a swarm intelligence as algorithm. Along with these algorithms, a genetic algorithm has been also introduced by adjusting and designing the parameters and design algorithms has been introduced to discover of crypt key. There are attempts to evaluate the performance of different algorithms for cryptanalysis of the SDES encryption algorithm.
Atefeh Mortazavi, Dr Farhad Soleimanian Gharehchopogh,
Volume 8, Issue 1 (9-2019)
Abstract
Emails are one of the fastest economic communications. Increasing email users has caused the increase of spam in recent years. As we know, spam not only damages user’s profits, time-consuming and bandwidth, but also has become as a risk to efficiency, reliability, and security of a network. Spam developers are always trying to find ways to escape the existing filters, therefore new filters to detect spams need to be developed. Most of these filters take advantage of a combination of several methods, such as black or white lists, using keywords, rule-based filters, machine learning methods and so on, to identify spams more accurately. many approaches about email spam detection exhausted up to now. In this paper, we propose a new approach for spam detection based on Particle Swarm Optimization Algorithm and K-Nearest Neighbor optimization, and we measure performance based on Accuracy, Precision, Recall, And f-measure. The results show that the proposed approach has a better performance than other models and the basic algorithms.
Mohammad Darvishi, Majid Ghayoori,
Volume 8, Issue 2 (2-2020)
Abstract
Intrusion detection systems are responsible for diagnosing and detecting any unauthorized use of the system, exploitation or destruction, which is able to prevent cyber-attacks using the network package analysis. one of the major challenges in the use of these tools is lack of educational patterns of attacks on the part of the engine analysis; engine failure that caused the complete training, the result is in production of high volumes of false warnings. On the other hand, the high level of intrusion detection training time will cause a significant delay in the training system. Therefore, in the analysis section of the intrusion detection system, we need to use an algorithm that shows significant performance with the least educational data, hidden Markov model is one of these successful algorithms in this field.
This Research also is trying to provide a misuse based intrusion detection solution with the focus of the evolutionary Hidden Markov model, the EHMM, which is designed to overcome the challenges posed. The most important part of hidden Markov model is to adjust the values of the parameters, the more adjusted values, optimal values would be more effective. The hidden Markov model is more likely to predict the probability of future values. Therefore, it has been trying to end the mail based on the causative analysis of NSL data sets-KDD using evolutionary programming algorithm for hidden Markov model for the optimal parameters and sort of teach it. Then, using it, the types of attacks in the dataset were identified. To evaluate the success rate in improving the accuracy percentage EHMM proposal intrusion detection, MATLAB System simulation environment has been implemented. The results of the investigation show fitted, EHMM plan, the percentage of the average is 87% of intrusion detection (if hidden Markov model is used normal) to over 92% (in the case of the hidden Markov model using evolutionary) increases. Also after training the training data in both methods based on conventional and evolutionary Markov model, the time of the target system for a training data set is approximately two hundred thousand record from low average of 489 minutes to more than 400 minutes has been dropped in the proposed method. This outcome achievement and making it operational on intrusion detection for the native system, can cause a defensive improvement which can be fitted in front of the other country for hostile cyber.
Seyed Ata S. Jafari, Mohammadhadi Alaeiyan, Aeed Parsa,
Volume 8, Issue 2 (2-2020)
Abstract
There is no doubt that malicious programs are one of the permanent threats to computer systems. Malicious programs distract the normal process of computer systems to apply their roguish purposes. Meanwhile, there is also a type of malware known as the ransomware that limits victims to access their computer system either by encrypting the victim's files or by locking the system. Despite other malicious families, ransomware families explicitly warn victims against its existence on the computer system. Although ransomwares are serious problems with computers, they can be detected with restricted footprints on victims’ computers. In this research, we provide a ransomware monitoring system which requires special environments to extract the malware filesystem's activities. A set of features based on filesystem's activities is extracted to classify ransomware families with an accuracy 98% by applying machine learning technique.
Mr Mohamad Jari, Miss Fariba Nazari,
Volume 8, Issue 2 (2-2020)
Abstract
The purpose of this study is to identify and prioritize the effective technical and technical stress factors of information security by IT experts identified in Aghajari oil and gas Exploitation Company. The statistical population of the study consisted of 100 ICT managers and experts in Aghajari Oil and Gas Co. which directly related to the security of information in the company, 80 of them were selected as samples. In this research, the first questionnaire was designed with the aim of identifying the factors and half-openness. The second questionnaire was designed with the aim of screening the identified factors as closed and based on Likert's five-choice spectrum. Finally, a third questionnaire was designed with the aim of determining the weights and rank of each one of the factors and in a pair comparison. The necessary analysis was carried out through the software SSS, Excel, ExpressChevis and MATLAB. The results of the research led to the identification of two main factors (occupational stressors and technical stressful factors influencing information security by IT experts in Aghajari oil and gas Exploitation Company) and 14 sub factors and then their rank were determined.
Farhad Soleimanian Gharehchopogh, Mohammad Sakhidek Hovshin,
Volume 9, Issue 1 (8-2020)
Abstract
Unfortunately, among internet services, users are faced with several unwanted messages that are not even related to their interests and scope, and they contain advertising or even malicious content. Spam email contains a huge collection of infected and malicious advertising emails that harms data destroying and stealing personal information for malicious purposes. In most cases, spam emails contain malware that is usually sent to users in the form of scripts or attachments, and the user infects the computer with malware by downloading and executing the attached file. In this paper, a new model for detecting spam e-mail is proposed based on the hybrid of the Harmony Search Algorithm (HAS) with the Magnetic Optimization Algorithm (MOA). The proposed model is used to select the effective features and then the classification is performed using the K Nearest Neighbor's (KNN) algorithm. In the proposed model, using the MOA was found the best features for the HSA, and the harmony matrix is formed based on them. Then the HSA changes based on the update and rate of step-change in each step of the harmony vectors so that the best vector is selected as the vector of characteristics among them. The results show that the accuracy of the proposed model on the Spam base dataset with 200 iterations is 94.17% and also the accuracy of the diagnostic model of the proposed model is more than other models.
Elnaz Katanchi, Babak Porghahramani,
Volume 9, Issue 2 (2-2021)
Abstract
The COVID-19 pandemic was a remarkable and unprecedented event that changed the lives of billions of citizens around the world and resulted in what is known as a new term in terms of social norms and lifestyles. In addition to the tremendous impact on society and business in general, the epidemic created a unique set of cybercrime circumstances that also affected society and business. Increased anxiety due to this epidemic increases the probability of success of cyber attacks by increasing the number and scope of cyber attacks. This article analyzes the COVID-19 epidemic from the perspective of cybercrime and highlights the wide range of cyberattacks experienced worldwide during the epidemic. Cyberattacks are analyzed in the context of major global events to reveal how cyberattacks work. This analysis shows how, following what appears to be a large gap between the outbreak in China and the first COVID-19-related cyberattack, attacks are steadily becoming more prevalent than in some on days, 3 or 4 unique cyber attacks were reported. This analysis uses surveys in the UK as a case study to show how cybercriminals use key events and government announcements to build and design cybercrime campaigns.
Dr Majid Fani, Dr Mohammadamin Torabi, Dr Matineh Moghaddam,
Volume 9, Issue 2 (2-2021)
Abstract
Not all phishing attacks are always done in the form of website forgery and telephone phishing. Emails and messages that appear to be sent by the bank and receive information from the user can also be a phishing attack. Feature selection and sample selection are two very important issues in the data processing stage in detecting malicious emails. In particular, identifying spam without data reduction will not be nearly as accurate in the results. Most articles and research have focused on one of these issues, and there are few articles that have worked in combination to detect malicious emails. Therefore, the purpose of the present study is to provide a method to reduce the data in identifying emails by selecting features and samples simultaneously. In the proposed method in this paper, the forbidden search algorithm and the genetic algorithm are used in combination and simultaneously. For the suitability of this method, the evaluation vector machine evaluation function was used. The results showed that the detection rate of spam and e-mails in LineSpam and UCI datasets was 97.28, which was the highest possible value compared to other algorithms proposed in previous studies.
|
|
