TAREK FRIKHA | Ecole Nationale d'Ingénieurs de Sfax (ENIS) (original) (raw)
Papers by TAREK FRIKHA
Lecture notes in networks and systems, 2023
Alexandria Engineering Journal
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2023
Multimedia Tools and Applications
2022 15th International Conference on Security of Information and Networks (SIN)
2022 15th International Conference on Security of Information and Networks (SIN)
2022 15th International Conference on Security of Information and Networks (SIN)
Voting is a basic element of running a country. Voting will continue to take place by physically ... more Voting is a basic element of running a country. Voting will continue to take place by physically entering the voting booth. No security is guaranteed for this operation, and several cases of tampering have been noted. In order to eliminate this type of problem, the paper proposes an online voting process with blockchain technology. With encryption and hashing, the security of each vote is ensured. The votes will be stored as transactions. A peer-to-peer network is leveraged to share this distributed ledger with voting transactions. The application is designed to hide the complexities of the architecture from the user. With the QR code, each student is uniquely identified. This ensures that each voter has only one chance to vote. With the public and private key, each node will have the ability to securely encrypt, hash, and add transactions to the blockchain. Votes cannot be traced back to the voters. This paper creates a peer-to-peer network with at least three peers. This paper plans to increase voter turnout through online voting. The scalability of blockchain applications depends on the secondary storage limits of peers.
arXiv (Cornell University), Nov 2, 2022
Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to ad... more Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in safety-critical and security-sensitive domains, such attacks may have catastrophic security and safety consequences. In this paper, we propose for the first time to use hardware-supported approximate computing to improve the robustness of machine-learning classifiers. we show that successful adversarial attacks against the exact classifier have poor transferability to the approximate implementation. Surprisingly, the robustness advantages also apply to white-box attacks where the attacker has unrestricted access to the approximate classifier implementation: in this case, we show that substantially higher levels of adversarial noise are needed to produce adversarial examples. Furthermore, our approximate computing model maintains the same level in terms of classification accuracy, does not require retraining, and reduces resource utilization and energy consumption of the CNN. We conducted extensive experiments on a set of strong adversarial attacks; We empirically show that the proposed implementation increases the robustness of a LeNet-5, Alexnet and VGG-11 CNNs considerably with up to 50% by-product saving in energy consumption due to the simpler nature of the approximate logic.
Electronics
In Tunisia, one of the major problems of the olive oil industry is marketing. Several factors hav... more In Tunisia, one of the major problems of the olive oil industry is marketing. Several factors have an impact, such as quality, originality, lobbying, subsidies and the certification of extra virgin olive oil. The major problem remains the traceability of the production process to guarantee the origin of the food at all times. This fine-grained traceability can be achieved by applying Blockchain technologies. Blockchain can be used as a solution that could bring visibility to the oil supply chain. It is proposed in order to guarantee the veracity of the product information at different stages. In this paper, a multi-Blockchain, multi-sensor traceability system using IoT will be presented. Two Blockchains that can be programmed via Smart Contract will be used. The first one is Quorum, which is a private Blockchain used by the actors of our system, and the second one is Ethereum, which is public and connects the different actors who have access to our system. This smart contract allows...
Smart Innovation, Systems and Technologies, 2022
Computational Intelligence and Neuroscience
The agricultural domain in developing countries is mostly dictated by archaic rules based on trad... more The agricultural domain in developing countries is mostly dictated by archaic rules based on traditions and inherited practices. With the evolution of digitalization and technology, it seems essential to apply new technologies to the agricultural field. Among the technologies to be exploited in agriculture, we mention sensors, IoT, WSN, cloud, blockchain, etc. We talk about smart agriculture in this case. In this paper, we propose a platform secured by blockchain for monitoring and securing production. This platform uses IoT connected sensors to track and save data. Our system is used to monitor the production process of olive trees. The goal is to track everything that enters and leaves our olive tree production from fertilizers, insecticides, and fortifiers to olives, trimming etc. The blockchain via its decentralized system allow a secure, irreversible, and clear monitoring. A dashboard allow us to highlight the changes while facilitating the work of farmers. Our prototype will b...
Computational Intelligence and Neuroscience
In the agricultural industry, wireless sensor networks (WSNs) can be an important tool to promote... more In the agricultural industry, wireless sensor networks (WSNs) can be an important tool to promote economic growth. Using network devices in agriculture has the potential to enhance the production process. One of the key challenges WSN faces is energy efficiency. A model based on the water pipeline method is proposed in order to efficiently utilize sensor nodes in agricultural production and water distribution. A water pipeline serves as an important structure for transporting potable water across a distance for consumption or irrigation. In contrast, the biggest transportation problems of water pipelines are leaks. So, water resources may be lost as a result. These pipes need real-time monitoring to prevent such problems. The wireless sensor network technique, however, is considered one of the best solutions available today for monitoring water pipelines. A detailed analysis of agriculture is provided by the model. Aspects of WSN are discussed and their agricultural use is expounded...
Journal of the Neurological Sciences, 2017
Magnetoencephalography and IEEG: intracerebral EEG) have a major contribution in the diagnosis of... more Magnetoencephalography and IEEG: intracerebral EEG) have a major contribution in the diagnosis of epilepsy. Following this diagnosis, an operation can be proposed to the patient, which aims to surgically remove the zone responsible for the seizures. It is therefore crucial to clearly define this area. Within this framework, two types of markers can be used; transient activities (epileptic spikes) and oscillations. However, these activities are difficult to separate because there is a frequency overlap between them.
Future Internet
With the onset of the COVID-19 pandemic and the succession of its waves, the transmission of this... more With the onset of the COVID-19 pandemic and the succession of its waves, the transmission of this disease and the number of deaths caused by it have been increasing. Despite the various vaccines, the COVID-19 virus is still contagious and dangerous for affected people. One of the remedies to this is precaution, and particularly social distancing. In the same vein, this paper proposes a remote voting system, which has to be secure, anonymous, irreversible, accessible, and simple to use. It therefore allows voters to have the possibility to vote for their candidate without having to perform the operation on site. This system will be used for university elections and particularly for student elections. We propose a platform based on a decentralized system. This system will use two blockchains communicating with each other: the public Ethereum blockchain and the private Quorum blockchain. The private blockchain will be institution-specific. All these blockchains send the necessary data ...
Big Data and Cognitive Computing
The evolution of applications in telecommunication, network, computing, and embedded systems has ... more The evolution of applications in telecommunication, network, computing, and embedded systems has led to the emergence of the Internet of Things and Artificial Intelligence. The combination of these technologies enabled improving productivity by optimizing consumption and facilitating access to real-time information. In this work, there is a focus on Industry 4.0 and Smart City paradigms and a proposal of a new approach to monitor and track water consumption using an OCR, as well as the artificial intelligence algorithm and, in particular the YoLo 4 machine learning model. The goal of this work is to provide optimized results in real time. The recognition rate obtained with the proposed algorithms is around 98%.
2022 IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS)
Electronics
With the evolution of information technology, the use of internet of things has increased. It aff... more With the evolution of information technology, the use of internet of things has increased. It affects several areas such as medical field, smart cities, and information systems. In this work, we will use this technological development in the context of health, particularly e-health. We present a platform based on IoMT to allow the monitoring of patient’s health. To meet the constraint of medical secrecy and confidentiality of information, we will use the Blockchain as a secure system. Our system will use the data collected by several smart sensors such as blood pressure, SPO2 concentration, and EEG signals. These encrypted data will be collected by an embedded Raspberry PI 4 platform (working as a smart data relay) before being processed (on a backend server) and then saved in an embedded Blockchain node. The preliminary results show the effectiveness of the proposed platform as a candidate of a low-cost example of secured Electronic Health Record (EHR).
2012 International Conference on High Performance Computing & Simulation (HPCS), 2012
ABSTRACT The emergency of multimedia applications particularly in mobile embedded systems puts ne... more ABSTRACT The emergency of multimedia applications particularly in mobile embedded systems puts new challenges for the design of such systems. The major difficulty is the embedded system's reduced energy and computational resources that must be carefully used to execute complex application often in unpredictable environments. So the system architecture must be energy efficient and flexible enough to adapt resources to application requirements to manage the environment architectures and mobile's constraints. The augmented reality is a very promising 3D embedded multimedia application. It's based on the addition of specific 3D's animations on a video flow. In this paper, we describe our concept of flexible architecture and we give implementation results based on Pixel Shader Accelerator. This is the first step of the project and we compare various hardware and software implementation.
7th International Conference on Design & Technology of Integrated Systems in Nanoscale Era, 2012
Virtual reality applications grow up nowadays. These applications are not only developed for the ... more Virtual reality applications grow up nowadays. These applications are not only developed for the PCs but also for embedded systems such as game console, Smartphone, touchpad… The limited touchpad resources and network communication between touchpad need an adaptation to environment noises. To solve this type of problem, we'll test a 3D application adaptation on FPGA platforms. These platforms will be simulated to touchpad. This application is assimilated to a virtual reality application. In this paper we describe the OS implementation results and the adaptation of the 3D application data to the network transfer [1].
Lecture notes in networks and systems, 2023
Alexandria Engineering Journal
Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 2023
Multimedia Tools and Applications
2022 15th International Conference on Security of Information and Networks (SIN)
2022 15th International Conference on Security of Information and Networks (SIN)
2022 15th International Conference on Security of Information and Networks (SIN)
Voting is a basic element of running a country. Voting will continue to take place by physically ... more Voting is a basic element of running a country. Voting will continue to take place by physically entering the voting booth. No security is guaranteed for this operation, and several cases of tampering have been noted. In order to eliminate this type of problem, the paper proposes an online voting process with blockchain technology. With encryption and hashing, the security of each vote is ensured. The votes will be stored as transactions. A peer-to-peer network is leveraged to share this distributed ledger with voting transactions. The application is designed to hide the complexities of the architecture from the user. With the QR code, each student is uniquely identified. This ensures that each voter has only one chance to vote. With the public and private key, each node will have the ability to securely encrypt, hash, and add transactions to the blockchain. Votes cannot be traced back to the voters. This paper creates a peer-to-peer network with at least three peers. This paper plans to increase voter turnout through online voting. The scalability of blockchain applications depends on the secondary storage limits of peers.
arXiv (Cornell University), Nov 2, 2022
Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to ad... more Machine-learning architectures, such as Convolutional Neural Networks (CNNs) are vulnerable to adversarial attacks: inputs crafted carefully to force the system output to a wrong label. Since machine-learning is being deployed in safety-critical and security-sensitive domains, such attacks may have catastrophic security and safety consequences. In this paper, we propose for the first time to use hardware-supported approximate computing to improve the robustness of machine-learning classifiers. we show that successful adversarial attacks against the exact classifier have poor transferability to the approximate implementation. Surprisingly, the robustness advantages also apply to white-box attacks where the attacker has unrestricted access to the approximate classifier implementation: in this case, we show that substantially higher levels of adversarial noise are needed to produce adversarial examples. Furthermore, our approximate computing model maintains the same level in terms of classification accuracy, does not require retraining, and reduces resource utilization and energy consumption of the CNN. We conducted extensive experiments on a set of strong adversarial attacks; We empirically show that the proposed implementation increases the robustness of a LeNet-5, Alexnet and VGG-11 CNNs considerably with up to 50% by-product saving in energy consumption due to the simpler nature of the approximate logic.
Electronics
In Tunisia, one of the major problems of the olive oil industry is marketing. Several factors hav... more In Tunisia, one of the major problems of the olive oil industry is marketing. Several factors have an impact, such as quality, originality, lobbying, subsidies and the certification of extra virgin olive oil. The major problem remains the traceability of the production process to guarantee the origin of the food at all times. This fine-grained traceability can be achieved by applying Blockchain technologies. Blockchain can be used as a solution that could bring visibility to the oil supply chain. It is proposed in order to guarantee the veracity of the product information at different stages. In this paper, a multi-Blockchain, multi-sensor traceability system using IoT will be presented. Two Blockchains that can be programmed via Smart Contract will be used. The first one is Quorum, which is a private Blockchain used by the actors of our system, and the second one is Ethereum, which is public and connects the different actors who have access to our system. This smart contract allows...
Smart Innovation, Systems and Technologies, 2022
Computational Intelligence and Neuroscience
The agricultural domain in developing countries is mostly dictated by archaic rules based on trad... more The agricultural domain in developing countries is mostly dictated by archaic rules based on traditions and inherited practices. With the evolution of digitalization and technology, it seems essential to apply new technologies to the agricultural field. Among the technologies to be exploited in agriculture, we mention sensors, IoT, WSN, cloud, blockchain, etc. We talk about smart agriculture in this case. In this paper, we propose a platform secured by blockchain for monitoring and securing production. This platform uses IoT connected sensors to track and save data. Our system is used to monitor the production process of olive trees. The goal is to track everything that enters and leaves our olive tree production from fertilizers, insecticides, and fortifiers to olives, trimming etc. The blockchain via its decentralized system allow a secure, irreversible, and clear monitoring. A dashboard allow us to highlight the changes while facilitating the work of farmers. Our prototype will b...
Computational Intelligence and Neuroscience
In the agricultural industry, wireless sensor networks (WSNs) can be an important tool to promote... more In the agricultural industry, wireless sensor networks (WSNs) can be an important tool to promote economic growth. Using network devices in agriculture has the potential to enhance the production process. One of the key challenges WSN faces is energy efficiency. A model based on the water pipeline method is proposed in order to efficiently utilize sensor nodes in agricultural production and water distribution. A water pipeline serves as an important structure for transporting potable water across a distance for consumption or irrigation. In contrast, the biggest transportation problems of water pipelines are leaks. So, water resources may be lost as a result. These pipes need real-time monitoring to prevent such problems. The wireless sensor network technique, however, is considered one of the best solutions available today for monitoring water pipelines. A detailed analysis of agriculture is provided by the model. Aspects of WSN are discussed and their agricultural use is expounded...
Journal of the Neurological Sciences, 2017
Magnetoencephalography and IEEG: intracerebral EEG) have a major contribution in the diagnosis of... more Magnetoencephalography and IEEG: intracerebral EEG) have a major contribution in the diagnosis of epilepsy. Following this diagnosis, an operation can be proposed to the patient, which aims to surgically remove the zone responsible for the seizures. It is therefore crucial to clearly define this area. Within this framework, two types of markers can be used; transient activities (epileptic spikes) and oscillations. However, these activities are difficult to separate because there is a frequency overlap between them.
Future Internet
With the onset of the COVID-19 pandemic and the succession of its waves, the transmission of this... more With the onset of the COVID-19 pandemic and the succession of its waves, the transmission of this disease and the number of deaths caused by it have been increasing. Despite the various vaccines, the COVID-19 virus is still contagious and dangerous for affected people. One of the remedies to this is precaution, and particularly social distancing. In the same vein, this paper proposes a remote voting system, which has to be secure, anonymous, irreversible, accessible, and simple to use. It therefore allows voters to have the possibility to vote for their candidate without having to perform the operation on site. This system will be used for university elections and particularly for student elections. We propose a platform based on a decentralized system. This system will use two blockchains communicating with each other: the public Ethereum blockchain and the private Quorum blockchain. The private blockchain will be institution-specific. All these blockchains send the necessary data ...
Big Data and Cognitive Computing
The evolution of applications in telecommunication, network, computing, and embedded systems has ... more The evolution of applications in telecommunication, network, computing, and embedded systems has led to the emergence of the Internet of Things and Artificial Intelligence. The combination of these technologies enabled improving productivity by optimizing consumption and facilitating access to real-time information. In this work, there is a focus on Industry 4.0 and Smart City paradigms and a proposal of a new approach to monitor and track water consumption using an OCR, as well as the artificial intelligence algorithm and, in particular the YoLo 4 machine learning model. The goal of this work is to provide optimized results in real time. The recognition rate obtained with the proposed algorithms is around 98%.
2022 IEEE International Conference on Design & Test of Integrated Micro & Nano-Systems (DTS)
Electronics
With the evolution of information technology, the use of internet of things has increased. It aff... more With the evolution of information technology, the use of internet of things has increased. It affects several areas such as medical field, smart cities, and information systems. In this work, we will use this technological development in the context of health, particularly e-health. We present a platform based on IoMT to allow the monitoring of patient’s health. To meet the constraint of medical secrecy and confidentiality of information, we will use the Blockchain as a secure system. Our system will use the data collected by several smart sensors such as blood pressure, SPO2 concentration, and EEG signals. These encrypted data will be collected by an embedded Raspberry PI 4 platform (working as a smart data relay) before being processed (on a backend server) and then saved in an embedded Blockchain node. The preliminary results show the effectiveness of the proposed platform as a candidate of a low-cost example of secured Electronic Health Record (EHR).
2012 International Conference on High Performance Computing & Simulation (HPCS), 2012
ABSTRACT The emergency of multimedia applications particularly in mobile embedded systems puts ne... more ABSTRACT The emergency of multimedia applications particularly in mobile embedded systems puts new challenges for the design of such systems. The major difficulty is the embedded system's reduced energy and computational resources that must be carefully used to execute complex application often in unpredictable environments. So the system architecture must be energy efficient and flexible enough to adapt resources to application requirements to manage the environment architectures and mobile's constraints. The augmented reality is a very promising 3D embedded multimedia application. It's based on the addition of specific 3D's animations on a video flow. In this paper, we describe our concept of flexible architecture and we give implementation results based on Pixel Shader Accelerator. This is the first step of the project and we compare various hardware and software implementation.
7th International Conference on Design & Technology of Integrated Systems in Nanoscale Era, 2012
Virtual reality applications grow up nowadays. These applications are not only developed for the ... more Virtual reality applications grow up nowadays. These applications are not only developed for the PCs but also for embedded systems such as game console, Smartphone, touchpad… The limited touchpad resources and network communication between touchpad need an adaptation to environment noises. To solve this type of problem, we'll test a 3D application adaptation on FPGA platforms. These platforms will be simulated to touchpad. This application is assimilated to a virtual reality application. In this paper we describe the OS implementation results and the adaptation of the 3D application data to the network transfer [1].