Academic & Scientific Articles

Permanent URI for this communityhttp://dl.cerist.dz/handle/CERIST/3

Browse

Search Results

Now showing 1 - 10 of 45

Combining Tags and Reviews to Improve Social Book Search Performance
(Springer, 2018-08-15) Chaa, Messaoud; Nouali, Omar; Bellot, Patrice
The emergence of Web 2.0 and social networks have provided important amounts of information that led researchers from different fields to exploit it. Social information retrieval is one of the areas that aim to use this social information to improve the information retrieval performance. This information can be textual, like tags or reviews, or non textual like ratings, number of likes, number of shares, etc. In this paper, we focus on the integration of social textual information in the research model. As it seems logical that integrating tags in the retrieval model should not be in the same way taken to integrate reviews, we will analyze the different influences of using tags and reviews on both the settings of retrieval parameters and the retrieval effectiveness. After several experiments, on the CLEF social book search collection, we concluded that combining the results obtained from two separate indexes and two models with specific parameters for tags and reviews gives good results compared to when using a single index and a single model.
TriDroid: a triage and classification framework for fast detection of mobile threats in android markets
(Springer-Verlag, 2021) Amira, Abdelouahab; Derhab, Abdelouahid; Karbab, ElMouatez Billah; Nouali, Omar; Aslam Khan , Farrukh
The Android platform is highly targeted by malware developers, which aim to infect the maximum number of mobile devices by uploading their malicious applications to different app markets. In order to keep a healthy Android ecosystem, app-markets check the maliciousness of newly submitted apps. These markets need to (a) correctly detect malicious app, and (b) speed up the detection process of the most likely dangerous applications among an overwhelming flow of submitted apps, to quickly mitigate their potential damages. To address these challenges, we propose TriDroid, a market-scale triage and classification system for Android apps. TriDroid prioritizes apps analysis according to their risk likelihood. To this end, we categorize the submitted apps as: botnet, general malware, and benign. TriDroid starts by performing a (1) Triage process, which applies a fast coarse-grained and less-accurate analysis on a continuous stream of the submitted apps to identify their corresponding queue in a three-class priority queuing system. Then, (2) the Classification process extracts fine-grained static features from the apps in the priority queue, and applies three-class machine learning classifiers to confirm with high accuracy the classification decisions of the triage process. In addition to the priority queuing model, we also propose a multi-server queuing model where the classification of each app category is run on a different server. Experiments on a dataset with more than 24K malicious and 3K benign applications show that the priority model offers a trade-off between waiting time and processing overhead, as it requires only one server compared to the multi-server model. Also it successfully prioritizes malicious apps analysis, which allows a short waiting time for dangerous applications compared to the FIFO policy.
SHARE-ABE: an efficient and secure data sharing framework based on ciphertext-policy attribute-based encryption and Fog computing
(Springer, 2022) Saidi, Ahmed; Nouali, Omar; Amira, Abdelouahab
Attribute-based encryption (ABE) is an access control mechanism that ensures efficient data sharing among dynamic groups of users by setting up access structures indicating who can access what. However, ABE suffers from expensive computation and privacy issues in resource-constrained environments such as IoT devices. In this paper, we present SHARE-ABE, a novel collaborative approach for preserving privacy that is built on top of Ciphertext-Policy Attribute-Based Encryption (CP-ABE). Our approach uses Fog computing to outsource the most laborious decryption operations to Fog nodes. The latter collaborate to partially decrypt the data using an original and efficient chained architecture. Additionally, our approach preserves the privacy of the access policy by introducing false attributes. Furthermore, we introduce a new construction of a collaboration attribute that allows users within the same group to combine their attributes while satisfying the access policy. Experiments and analyses of the security properties demonstrate that the proposed scheme is secure and efficient especially for resource-constrained IoT devices.
Minimum redundancy and maximum relevance for single and multi-document Arabic text summarization
(Elsevier, 2014-12) Oufaida, Houda; Nouali, Omar; Blache, Philippe
Automatic text summarization aims to produce summaries for one or more texts using machine techniques. In this paper, we propose a novel statistical summarization system for Arabic texts. Our system uses a clustering algorithm and an adapted discriminant analysis method: mRMR (minimum redundancy and maximum relevance) to score terms. Through mRMR analysis, terms are ranked according to their discriminant and coverage power. Second, we propose a novel sentence extraction algorithm which selects sentences with top ranked terms and maximum diversity. Our system uses minimal language-dependant processing: sentence splitting, tokenization and root extraction. Experimental results on EASC and TAC 2011 MultiLingual datasets showed that our proposed approach is competitive to the state of the art systems.
Lifetime-Aware Backpressure : A New Delay-Enhanced Backpressure-Based Routing Protocol
(IEEE, 2019-03) Kabou, Abdelbaset; Nouali-Taboudjemat, Nadia; Djahel, Soufiene; Yahiaoui, Saïd; Nouali, Omar
Dynamic backpressure is a highly desirable family of routing protocols known for their attractive mathematical properties. However, these protocols suffer from a high end-to-end delay making them inefficient for real-time traffic with strict end-to-end delay requirements. In this paper, we address this issue by proposing a new adjustable and fully distributed backpressure-based scheme with low queue management complexity, named Lifetime-Aware Backpressure (LTA-BP). The novelty in the proposed scheme consists in introducing the urgency level as a new metric for service differentiation among the competing traffic flows in the network. Our scheme not just significantly improves the quality of service provided for real-time traffic with stringent end-to-end delay constraints, but interestingly protects also the flows with softer delay requirements from being totally starved. The proposed scheme has been evaluated and compared against other state-of-the-art routing protocol, using computer simulation, and the obtained results show its superiority in terms of the achieved end-to-end delay and throughput.
Using ABE for Medical Data Protection in Fog Computing
(2019-05-03) Krinah, Abdelghani; Challal, Yacine; Omar, Mawloud; Nouali, Omar
Fog is an extension of the cloud computing paradigm, developed to fix the clouds latency, especially for applications requiring a very short response time, such as e-health applications. However, these applications also require a high level of data confidentiality, hence the need to apply appropriate encryption techniques, which can ensure security needs, while respecting the characteristics of the infrastructures devices. In this article, we will focus on ABE encryption, through the work done to study its applicability in the cloud and the Internet of things, as well as the improvements that can be made to adapt it to the fog computing environment.
Secure Inverted Index Based Search over Encrypted Cloud Data with User Access Rights Management
(Springer, 2019-01-18) Boucenna, Fateh; Nouali, Omar; Kechid, Samir; Kechadi, M. Tahar
Cloud computing is a technology that provides users with a large storage space and an enormous computing power. However, the outsourced data are often sensitive and confidential, and hence must be encrypted before being outsourced. Consequently, classical search approaches have become obsolete and new approaches that are compatible with encrypted data have become a necessity. For privacy reasons, most of these approaches are based on the vector model which is a time consuming process since the entire index must be loaded and exploited during the search process given that the query vector must be compared with each document vector. To solve this problem, we propose a new method for constructing a secure inverted index using two key techniques, homomorphic encryption and the dummy documents technique. However, 1) homomorphic encryption generates very large ciphertexts which are thousands of times larger than their corresponding plaintexts, and 2) the dummy documents technique that enhances the index security produces lots of false positives in the search results. The proposed approach exploits the advantages of these two techniques by proposing two methods called the compressed table of encrypted scores and the double score formula. Moreover, we exploit a second secure inverted index in order to manage the users’ access rights to the data. Finally, in order to validate our approach, we performed an experimental study using a data collection of one million documents. The experiments show that our approach is many times faster than any other approach based on the vector model.
Toward a new Backpressure-based framework to Enhance Situational Awareness in Disaster Response
(IEEE ICT-DM-2017, 2017-12-11) Kabou, Abdelbaset; Nouali-Taboudjemat, Nadia; Nouali, Omar
Crises generate intense need to communication not just as a panic reaction to crisis, but also due the critical need for communication in order to better coordinate during response activities. In the afterward of a disaster, the lack of resources to handle this increase of data, due to the fragility of network infrastructures, leads to network congestion or overload. The results is that critical data are prevented from reaching decision makers, which has a direct impact on situational-awareness. To overcome this problem, we propose a new cross layer architecture for Wireless Mesh Network with a twofold objective: one, to include a filtering system able to identify the most critical data and two, to propose a routing layer with the capacity to prioritize these data while ensuring the stability and throughput optimality of the whole network. The proposed solution combines both by proposing an adjustable and fully distributed version of the high throughput efficient Backpressure routing protocol, with a geolocation and role-based filtering and prioritizing system. Both components collaborate in a way to identify and send most critical data, using a lower end-to-end delay, without however starving less critical data. Extensive experiments, using NS-3 simulator, are used to validate the proposal and confirm the high impact of the introduced ideas
New Technique to Deal With Verbose Queries in Social Book Search
(CERIST, 2017) Chaa, Messaoud; Nouali, Omar; Bellot, Patrice
Verbose query reduction and query term weighting are automatic techniques to deal with verbose queries. The objective is either to assign an appropriate weight to query terms according to their importance in the topic, or outright remove unsuitable terms from the query and keep only the suitable terms to the topic and user’s need. These techniques improve performance and provide good results for ad hoc information retrieval. In this paper we propose a new approach to deal with long verbose queries in Social Information Re-trieval (SIR) by taking Social Book Search as an example. In this approach, a new statistical measure was introduced to reduce and weight terms of verbose queries. Next, we expand he query by exploiting the similar books mentioned by users in their queries. We find that the proposed approach improves significantly the results.
Accelerated Search over Encrypted Cloud Data
(IEEE, 2017-02-13) Boucenna, Fateh; Nouali, Omar; Dabah, Adel; Kechid, Samir
Companies and other organizations such as hospitals seek more and more to enjoy the benefits of cloud computingin terms of storage space and computing power. However, outsourced data must be encrypted in order to be protected againstpossible attacks. Therefore, traditional information retrieval systems (IRS) are no longer effective and must be adapted in order towork over encrypted cloud data. In addition, in order to providethe ability to search over an encrypted index, we use the vectormodel to represent documents and queries which is the most usedin the literature. During the search process, the query vectormust be compared with each document vector which is a time consuming process since the data collection is generally huge.Consequently, the search performance is degraded and the searchprocess is too slow. To overcome this drawback, we proposethe use of High Performance Computing (HPC) architecturesto accelerate the search over encrypted cloud data. Indeed,we propose several techniques that take benefit from Graphics Processing Unit (GPU) and computer cluster architectures by distributing the work between different threads. In addition,in order to get the best performance, we design our solutionsso that they can process several queries simultaneously. Theexperimental study using 400.000 documents demonstrates theefficiency of our proposals by reaching a speed-up around 46x.

Academic & Scientific Articles

Browse

Filters

Settings

Sort By

Results per page

Search Results