Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945765
Marwa Massaâbi, J. Akaichi
The wide spread of the world wide web, the accelerating internet technologies development and the continuous upload of documents has produced large volumes of data. As a result, a huge amount of similar information is available on the web however very difficult to retrieve the best, concise and most precise one. In addition, the continuous upload of information leads to another issue which is documents' redundancy. It still an issue that irritates researchers due to the multiplicity of duplicated documents. Hence, the unsatisfaction of the user is due to the irrelevance and the multiple duplications in the search results. Therefore, the need to study the fields of information retrieval and document similarity is essential to ameliorate the results. Working on retrieving and comparing information, then deleting duplications will finally achieve the needed results in short time and efficient way. For this reason, we propose, in this paper, a new approach which detects and deletes automatically duplicated research results. This approach is based on fuzzy logic and distance measurements. In fact, it has shown promising results.
{"title":"A fuzzy similarity measure for search results evaluation","authors":"Marwa Massaâbi, J. Akaichi","doi":"10.1109/AICCSA.2016.7945765","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945765","url":null,"abstract":"The wide spread of the world wide web, the accelerating internet technologies development and the continuous upload of documents has produced large volumes of data. As a result, a huge amount of similar information is available on the web however very difficult to retrieve the best, concise and most precise one. In addition, the continuous upload of information leads to another issue which is documents' redundancy. It still an issue that irritates researchers due to the multiplicity of duplicated documents. Hence, the unsatisfaction of the user is due to the irrelevance and the multiple duplications in the search results. Therefore, the need to study the fields of information retrieval and document similarity is essential to ameliorate the results. Working on retrieving and comparing information, then deleting duplications will finally achieve the needed results in short time and efficient way. For this reason, we propose, in this paper, a new approach which detects and deletes automatically duplicated research results. This approach is based on fuzzy logic and distance measurements. In fact, it has shown promising results.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122212739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945638
Mohamed Abouzahir, A. Elouardi, S. Bouaziz, O. Hammami, Ismail Ali
The development of SLAM algorithms in the era of autonomous navigation and the growing demand for autonomous robot in place of human being, has put into question how to reduce the computational complexity and make use of these algorithms to operate in real time. Our work aims to take advantage of the high level synthesis (HLS) on FPGAs to design a real time SLAM application. Precisely, we evaluate the promess-held by the new modern low power FPGAs in accelerating SLAM algorithms. Throughtout this, we will attempt to implement a well-known algorithms (FastSLAM2.0), on a new modern FPGA using OpenCL, a standard high level language. Our implementation results show a significant improvement of the algorithm processing time on an FPGA device over a modern powerful embedded GPGPU.
{"title":"High-level synthesis for FPGA design based-SLAM application","authors":"Mohamed Abouzahir, A. Elouardi, S. Bouaziz, O. Hammami, Ismail Ali","doi":"10.1109/AICCSA.2016.7945638","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945638","url":null,"abstract":"The development of SLAM algorithms in the era of autonomous navigation and the growing demand for autonomous robot in place of human being, has put into question how to reduce the computational complexity and make use of these algorithms to operate in real time. Our work aims to take advantage of the high level synthesis (HLS) on FPGAs to design a real time SLAM application. Precisely, we evaluate the promess-held by the new modern low power FPGAs in accelerating SLAM algorithms. Throughtout this, we will attempt to implement a well-known algorithms (FastSLAM2.0), on a new modern FPGA using OpenCL, a standard high level language. Our implementation results show a significant improvement of the algorithm processing time on an FPGA device over a modern powerful embedded GPGPU.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121161488","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945830
Moulay Smail Bouzakraoui, A. Sadiq, N. Enneya
Automated analysis of human affective behavior has attracted increasing attention from researchers in psychology neuroscience, linguistics, computer science and related disciplines. Nowadays, emotional factors are important as classic functional aspects of customer purchasing behavior. Recent studies have shown that most of our purchasing choices and decisions are the result of a careful analysis of the product advantages and disadvantages and of affective and emotional aspects. Psychological literature recognizes that the emotional conditions are always present and influence every stage of decision-making in purchasing process. The main contribution of this paper is the design of a novel framework that provides the essential for customer sentiments analysis and emotion measuring in marketing. We focus our study on automatic facial expression analysis as a tool for measuring emotional customer that can predict their behavior in the decision-making.
{"title":"Towards a framework for customer emotion detection","authors":"Moulay Smail Bouzakraoui, A. Sadiq, N. Enneya","doi":"10.1109/AICCSA.2016.7945830","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945830","url":null,"abstract":"Automated analysis of human affective behavior has attracted increasing attention from researchers in psychology neuroscience, linguistics, computer science and related disciplines. Nowadays, emotional factors are important as classic functional aspects of customer purchasing behavior. Recent studies have shown that most of our purchasing choices and decisions are the result of a careful analysis of the product advantages and disadvantages and of affective and emotional aspects. Psychological literature recognizes that the emotional conditions are always present and influence every stage of decision-making in purchasing process. The main contribution of this paper is the design of a novel framework that provides the essential for customer sentiments analysis and emotion measuring in marketing. We focus our study on automatic facial expression analysis as a tool for measuring emotional customer that can predict their behavior in the decision-making.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"51 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113941007","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945691
Oumaima Ben Abderrahim, Mohamed Houcine Elhedhili, L. Saïdane
The Internet of Things (IoT) is based on the idea that things surrounding the human living space can be connected to the Internet, allowing smarter living environments and more comfortable life. However, adoption of the IoT might not be approved unless security issues are solved. In this paper, we propose a new Dirichlet based trust management system for the IoT called DTMS-IoT. This system detects nodes malicious behaviour which permits to mitigate both on-off attacks and dishonest recommendations. It also uses service levels and things capacities to reinforce security. As in many trust management systems introduced in the literature, the computation of trust in our solution is based on direct observations and recommendations. The novelty of our approach can be summed up in two aspects. The first aspect concerns recommendations that we do not consider unless direct observations are not credible. However the second aspect tries to prevent On-Off attacks using the precaution factor and mitigates dishonest recommendations based on k-means selection algorithm and guarantor things. The effectiveness of the proposed system is proved by simulation against on-off attacks and good/bad mouthing attacks.
{"title":"DTMS-IoT: A Dirichlet-based trust management system mitigating on-off attacks and dishonest recommendations for the Internet of Things","authors":"Oumaima Ben Abderrahim, Mohamed Houcine Elhedhili, L. Saïdane","doi":"10.1109/AICCSA.2016.7945691","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945691","url":null,"abstract":"The Internet of Things (IoT) is based on the idea that things surrounding the human living space can be connected to the Internet, allowing smarter living environments and more comfortable life. However, adoption of the IoT might not be approved unless security issues are solved. In this paper, we propose a new Dirichlet based trust management system for the IoT called DTMS-IoT. This system detects nodes malicious behaviour which permits to mitigate both on-off attacks and dishonest recommendations. It also uses service levels and things capacities to reinforce security. As in many trust management systems introduced in the literature, the computation of trust in our solution is based on direct observations and recommendations. The novelty of our approach can be summed up in two aspects. The first aspect concerns recommendations that we do not consider unless direct observations are not credible. However the second aspect tries to prevent On-Off attacks using the precaution factor and mitigates dishonest recommendations based on k-means selection algorithm and guarantor things. The effectiveness of the proposed system is proved by simulation against on-off attacks and good/bad mouthing attacks.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123758473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945742
Lacheheb Hadjer, Saliha Aouat
Searching an image in a huge set of images became an important task in several domains such as crime, medicine, geology and so on. The task of retrieving images by their visual contents is called content-based image retrieval (CBIR) systems. These systems have to be fast, efficient and semantically similar. For this aim, we used a new density clustering technique in our proposed CBIR system. The paper describes a new CBIR that uses a t-SNE (t-Distributed Stochastic Neighbor Embedding) data reduction and a proposed density-based clustering method. Several advantages are deduced from the proposition. First, reducing the dimensionality minimizes the required time and storage space. Next, reducing images to a very low dimension such as 2D or 3D permits an easier visualization. Also, no need to set image data parameters for clustering. Likewise, No need to introduce the number of clusters. Besides, it is effective for several image data especially shaped data. For validation tests, we use ZUBUD, Wang databases and shape datasets. Several comparison with two other CBIR systems such as FIRE and LIRE are included. The results obtained demonstrate the originality, reliability, and relevance of our proposition.
{"title":"A density clustering approach for CBIR system","authors":"Lacheheb Hadjer, Saliha Aouat","doi":"10.1109/AICCSA.2016.7945742","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945742","url":null,"abstract":"Searching an image in a huge set of images became an important task in several domains such as crime, medicine, geology and so on. The task of retrieving images by their visual contents is called content-based image retrieval (CBIR) systems. These systems have to be fast, efficient and semantically similar. For this aim, we used a new density clustering technique in our proposed CBIR system. The paper describes a new CBIR that uses a t-SNE (t-Distributed Stochastic Neighbor Embedding) data reduction and a proposed density-based clustering method. Several advantages are deduced from the proposition. First, reducing the dimensionality minimizes the required time and storage space. Next, reducing images to a very low dimension such as 2D or 3D permits an easier visualization. Also, no need to set image data parameters for clustering. Likewise, No need to introduce the number of clusters. Besides, it is effective for several image data especially shaped data. For validation tests, we use ZUBUD, Wang databases and shape datasets. Several comparison with two other CBIR systems such as FIRE and LIRE are included. The results obtained demonstrate the originality, reliability, and relevance of our proposition.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125078357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945653
Ayoub Ellahyani, Mohamed El Ansari
Traffic Sign Detection and Recognition is an important component of intelligent transportation systems. It has captured the attention of the computer vision community for several decades. In this paper, we propose a new traffic sign detection and recognition approach consisting of color segmentation, shape classification and recognition stages. In the first stage, the image is segmented using look-up tables and thresholding on the HSI color space. The second stage uses Distance to borders (DtBs) features and random forest classifier to detect circular, triangular and rectangular shapes among the segmented ROIs. The last stage consists in the recognition of the detected signs. It is performed using Random Forest as classifier and histogram of oriented gradients (HOG) together with local self-similarity (LSS) as features. Experimental results show that the proposed method achieves high recall, precision, and correct classification accuracy ratios, and is robust to various adverse situations.
{"title":"Complementary features for traffic sign detection and recognition","authors":"Ayoub Ellahyani, Mohamed El Ansari","doi":"10.1109/AICCSA.2016.7945653","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945653","url":null,"abstract":"Traffic Sign Detection and Recognition is an important component of intelligent transportation systems. It has captured the attention of the computer vision community for several decades. In this paper, we propose a new traffic sign detection and recognition approach consisting of color segmentation, shape classification and recognition stages. In the first stage, the image is segmented using look-up tables and thresholding on the HSI color space. The second stage uses Distance to borders (DtBs) features and random forest classifier to detect circular, triangular and rectangular shapes among the segmented ROIs. The last stage consists in the recognition of the detected signs. It is performed using Random Forest as classifier and histogram of oriented gradients (HOG) together with local self-similarity (LSS) as features. Experimental results show that the proposed method achieves high recall, precision, and correct classification accuracy ratios, and is robust to various adverse situations.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"68 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114000009","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945680
M. Elgharbawy, A. Schwarzhaupt, Gerrit Scheike, Michael Frey, F. Gauterin
This paper deals with an advanced approach for the verification of ADAS algorithms in complex automotive sensor networks. We introduce a real-time modular framework that can benchmark the performance of the ADAS algorithms at the electronic system level using a Hardware-in-the-Loop (HiL) co-simulation. The presented research provides a generic architecture of ADAS sensor error injection for robustness testing of the System under Test (SuT). Effects of sensor failures can be added in a continuous manner to achieve increased degrees of realism. For efficient verification, an astute selection of relevant test scenarios is conducted using model-based testing to avoid repetitive test scenarios. The industry-proven framework facilitates a systematic testing of ADAS algorithms precisely and more efficiently on the target electronic control unit (ECU) in the laboratory.
{"title":"A generic architecture of ADAS sensor fault injection for virtual tests","authors":"M. Elgharbawy, A. Schwarzhaupt, Gerrit Scheike, Michael Frey, F. Gauterin","doi":"10.1109/AICCSA.2016.7945680","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945680","url":null,"abstract":"This paper deals with an advanced approach for the verification of ADAS algorithms in complex automotive sensor networks. We introduce a real-time modular framework that can benchmark the performance of the ADAS algorithms at the electronic system level using a Hardware-in-the-Loop (HiL) co-simulation. The presented research provides a generic architecture of ADAS sensor error injection for robustness testing of the System under Test (SuT). Effects of sensor failures can be added in a continuous manner to achieve increased degrees of realism. For efficient verification, an astute selection of relevant test scenarios is conducted using model-based testing to avoid repetitive test scenarios. The industry-proven framework facilitates a systematic testing of ADAS algorithms precisely and more efficiently on the target electronic control unit (ECU) in the laboratory.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122445595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945687
C. Thomson, Isam Wadhaj, I. Romdhani, A. Al-Dubai
An examination of existing studies in the area of Routing Protocol for Low-Power and Lossy Networks (RPL) implementation in wireless sensor networks (WSNs) reveals a consistent approach taken of optimal node distribution. This in order to best evaluate networking metrics such as Packet Delivery Ratio (PDR), latency and energy consumption. The tests detailed in this paper differ from previous work, in that there is no concerted effort to ensure the appropriate density of the network topologies. The intention being to ‘strain’ the limits of the transmission ranges. Using the Cooja simulator, we take the approach of utilising nodes in less-than perfect, real-world scenarios. In this way the main factor at play is the ability to retain nodes as part of the Destination Oriented Directed Acyclic Graph (DODAG) build in environments with ‘strained’ transmission ranges. In this regard we compare Objective Function Zero (OF0) Hop-count with The Minimum Rank with Hysteresis Objective Function (MRHOF) Energy and expected transmission count (ETX) metrics. In utilising the energy metric, a novel approach, we prove that it is ineffective in this scenario. Resultantly, the ETX metric outperforms Hop-count, producing results that improve over time, adjusting to ‘strained’ environments to include more motes in the DODAG build as time passes. In conclusion, we propose future work to develop an extension to Cooja to utilise the ETX metric with an Energy constraint. This in order to better evaluate the use of node energy levels as part of a DODAG build in ‘strained’ WSN implementations in the future.
{"title":"Performance evaluation of RPL metrics in environments with strained transmission ranges","authors":"C. Thomson, Isam Wadhaj, I. Romdhani, A. Al-Dubai","doi":"10.1109/AICCSA.2016.7945687","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945687","url":null,"abstract":"An examination of existing studies in the area of Routing Protocol for Low-Power and Lossy Networks (RPL) implementation in wireless sensor networks (WSNs) reveals a consistent approach taken of optimal node distribution. This in order to best evaluate networking metrics such as Packet Delivery Ratio (PDR), latency and energy consumption. The tests detailed in this paper differ from previous work, in that there is no concerted effort to ensure the appropriate density of the network topologies. The intention being to ‘strain’ the limits of the transmission ranges. Using the Cooja simulator, we take the approach of utilising nodes in less-than perfect, real-world scenarios. In this way the main factor at play is the ability to retain nodes as part of the Destination Oriented Directed Acyclic Graph (DODAG) build in environments with ‘strained’ transmission ranges. In this regard we compare Objective Function Zero (OF0) Hop-count with The Minimum Rank with Hysteresis Objective Function (MRHOF) Energy and expected transmission count (ETX) metrics. In utilising the energy metric, a novel approach, we prove that it is ineffective in this scenario. Resultantly, the ETX metric outperforms Hop-count, producing results that improve over time, adjusting to ‘strained’ environments to include more motes in the DODAG build as time passes. In conclusion, we propose future work to develop an extension to Cooja to utilise the ETX metric with an Energy constraint. This in order to better evaluate the use of node energy levels as part of a DODAG build in ‘strained’ WSN implementations in the future.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131371255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945735
H. Ahmadi, F. Viani, A. Polo, R. Bouallègue
Positioning and tracking of wireless devices in indoor environment is a challenging research problem. Accurate localization of a moving target is a fundamental requirement in Wireless Sensor Networks monitoring applications. In this paper, a novel location tracking algorithm which combines learning methods is proposed. In previous work, regression tree using received signal strength method is proposed to localize a static sensor node. This approach is employed in this paper to solve the complex relation between the received signal strength and the target position. Then, an ensemble of trees are applied leading to more accurate position of the moving target. The proposed algorithm has been experimentally evaluated using real measurement of a moving target in an office room. The performance results have been analyzed through a comparison with the standard regression tree and ordinary Kalman filter.
{"title":"Improved target tracking using regression tree in wireless sensor networks","authors":"H. Ahmadi, F. Viani, A. Polo, R. Bouallègue","doi":"10.1109/AICCSA.2016.7945735","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945735","url":null,"abstract":"Positioning and tracking of wireless devices in indoor environment is a challenging research problem. Accurate localization of a moving target is a fundamental requirement in Wireless Sensor Networks monitoring applications. In this paper, a novel location tracking algorithm which combines learning methods is proposed. In previous work, regression tree using received signal strength method is proposed to localize a static sensor node. This approach is employed in this paper to solve the complex relation between the received signal strength and the target position. Then, an ensemble of trees are applied leading to more accurate position of the moving target. The proposed algorithm has been experimentally evaluated using real measurement of a moving target in an office room. The performance results have been analyzed through a comparison with the standard regression tree and ordinary Kalman filter.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127985751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-11-01DOI: 10.1109/AICCSA.2016.7945801
Duaa Ekhtoom, M. Al-Ayyoub, Mohammed I. Al-Saleh, M. Alsmirat, Ismail Hmeidi
Metamorphic malware are able to change their appearance to evade detection by traditional anti-malware software. One of the ways to help mitigate the threat of new metamorphic malware is to determine their origins, i.e., the families to which they belong. This type of metamorphic malware analysis is not typically handled by commercial software. Moreover, existing works rely on analyzing the op-code sequences extracted from the Assembly files of the malware. Very few papers have tried to perform analysis on the binary files of the malware. However, they focused on the simple binary problem of differentiating between a certain malware family and benign files. In this work, we address the more difficult problem of determining the origin of a new metamorphic malware by measuring its similarity to hundreds of variants taken from 13 families of real malware. To address this problem, we use a compression-based classification approach. We experiment with two such approaches: AMDL and BCN. The results showed that AMDL performed no better than a random guess (11% accuracy for AMDL and 18% for the random baseline). On the other hand, BCN performed really well with 67% accuracy.
{"title":"A compression-based technique to classify metamorphic malware","authors":"Duaa Ekhtoom, M. Al-Ayyoub, Mohammed I. Al-Saleh, M. Alsmirat, Ismail Hmeidi","doi":"10.1109/AICCSA.2016.7945801","DOIUrl":"https://doi.org/10.1109/AICCSA.2016.7945801","url":null,"abstract":"Metamorphic malware are able to change their appearance to evade detection by traditional anti-malware software. One of the ways to help mitigate the threat of new metamorphic malware is to determine their origins, i.e., the families to which they belong. This type of metamorphic malware analysis is not typically handled by commercial software. Moreover, existing works rely on analyzing the op-code sequences extracted from the Assembly files of the malware. Very few papers have tried to perform analysis on the binary files of the malware. However, they focused on the simple binary problem of differentiating between a certain malware family and benign files. In this work, we address the more difficult problem of determining the origin of a new metamorphic malware by measuring its similarity to hundreds of variants taken from 13 families of real malware. To address this problem, we use a compression-based classification approach. We experiment with two such approaches: AMDL and BCN. The results showed that AMDL performed no better than a random guess (11% accuracy for AMDL and 18% for the random baseline). On the other hand, BCN performed really well with 67% accuracy.","PeriodicalId":448329,"journal":{"name":"2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134258040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：