International Journal Papers

Permanent URI for this collectionhttp://dl.cerist.dz/handle/CERIST/17

Browse

Author: search.filters.author.Challal, YacineHas files: Yes

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    PRIviLY: Private Remote Inference over fulLY connected deep networks for pervasive health monitoring with constrained client-side
    (Elsevier, 2023-09) Boulemtafes, Amine; Derhab, Abdelouahid; Challal, Yacine
    Remote deep learning paradigm enables to better leverage the power of deep neural networks in pervasive health monitoring (PHM) applications, especially by addressing the constrained client-side environment. However, remote deep learning in the context of PHM requires to ensure three properties: (1) meet the high accuracy requirement of the healthcare domain, (2) satisfy the client-side constraints, and (3) cope with the privacy requirements related to the high sensitivity of health data. Different privacy-preserving solutions for remote deep learning exit in the literature but many of them fail to fully address the PHM requirements especially with respect to constrained client-side environments. To that end, we propose PRIviLY, a novel privacy-preserving remote inference solution, designed specifically for the popular Fully Connected Deep Networks (FCDNs). PRIviLY avoids the use of encryption for privacy preservation of sensitive information, in order to fully prevent accuracy loss, and to alleviate the server-side hardware requirements. Besides, PRIviLY adopts a non-colluding two-server architecture, and leverages the linear computations of FCDNs along with reversible random perturbation and permutation techniques in order to preserve privacy of sensitive information, while meeting low overhead requirement of constrained client-sides. At the cloud server, efficiency evaluation shows that PRIviLY achieves an improvement ratio of 4 to more than 15 times for communication, and a minimum improvement ratio of 135 times for computation overhead. At the intermediate server, the minimum improvement ratio is at least more than 10,900 for computation, while for communication, the improvement ratio varies from 5 to more than 21 times. As for the client-side, PRIviLY incurs an additional overhead of about 27% in terms of communication, and between 16% and at most 27% in terms of computation.
  • Thumbnail Image
    Item
    Efficient data aggregation with in-network integrity control for WSN
    (Elsevier, 2012-10) Bagaa, Miloud; Challal, Yacine; Ouadjaout, Abdelraouf; Lasla, Noureddine; Badache, Nadjib
    Energy is a scarce resource in Wireless Sensor Networks (WSN). Some studies show that more than 70% of energy is consumed in data transmission in WSN. Since most of the time, the sensed information is redundant due to geographically collocated sensors, most of this energy can be saved through data aggregation. Furthermore, data aggregation improves bandwidth usage and reduces collisions due to interference. Unfortunately, while aggregation eliminates redundancy, it makes data integrity verification more complicated since the received data is unique. In this paper, we present a new protocol that provides control integrity for aggregation in wireless sensor networks. Our protocol is based on a two-hop verification mechanism of data integrity. Our solution is essentially different from existing solutions in that it does not require referring to the base station for verifying and detecting faulty aggregated readings, thus providing a totally distributed scheme to guarantee data integrity. We carried out numerical analysis and simulations using the TinyOS environment. Results show that the proposed protocol yields significant savings in energy consumption while preserving data integrity, and outperforms comparable solutions with respect to some important performance criteria.
  • Thumbnail Image
    Item
    Secure and efficient disjoint multipath construction for fault tolerant routing in wireless sensor networks
    (Elsevier, 2011-07) Challal, Yacine; Ouadjaout, Abdelraouf; Lasla, Noureddine; Bagaa, Miloud; Abdelkarim, Hadjidj
    In wireless sensor networks, reliability is a design goal of a primary concern. To build a comprehensive reliable system, it is essential to consider node failures and intruder attacks as unavoidable phenomena. In this paper, we present a new intrusion-fault tolerant routing scheme offering a high level of reliability through a secure multipath routing construction. Unlike existing intrusion-fault tolerant solutions, our protocol is based on a distributed and in-network verification scheme, which does not require any referring to the base station. Furthermore, it employs a new multipath selection scheme seeking to enhance the tolerance of the network and conserve the energy of sensors. Extensive analysis and simulations using TinyOS showed that our approach improves many important performance metrics such as: the mean time to failure of the network, detection overhead of some security attacks, energy consumption, and resilience.