Hanan El Bakkali

Mobile crowdsensing (MCS) is an emerging paradigm that enables cost-effective, large-scale, and participatory data collection through mobile devices. However, the open nature of MCS raises significant privacy and trust challenges. Existing reputation models have made progress in assessing the quality of contributions, but they still struggle to manage prolonged inactivity, which can lead to outdated scores that no longer reflect current engagement. To address these issues, this paper presents RBCrowd, a dynamic reputation management system based on a dual blockchain architecture. It consists of the Sensing Chain (SC), a public blockchain recording sensing tasks and results, and the Reputation Chain (RC), a consortium blockchain managing user reputation scores. To guarantee privacy, the framework limits identity verification to the RC, ensuring that data on the SC is stored without direct links to the worker. We paired this privacy mechanism with a reputation model that rewards consistent, high-quality contributions. The system updates reputation scores by first validating the specific task and then adjusting for historical engagement, specifically penalizing prolonged inactivity. We evaluate RBCrowd through simulations in realistic MCS scenarios, and the results show that our framework provides more effective dynamic trust management than existing models. It also achieves increased reliability and fairness while managing prolonged inactivity through adaptive penalties.

With the growing complexity of real-world cyber threats, organizations face increasing challenges in protecting their networks from attacks that often blend in with normal traffic. In practical settings, network data is frequently noisy and only a small portion of it is labeled, making intrusion detection a difficult task. Semi-supervised deep learning models, particularly autoencoders, have gained popularity for detecting unusual activity in network traffic. However, standard autoencoders often struggle to adapt to the unpredictable and noisy conditions found in real network environments, giving rise to overfitting and a higher rate of false alarms. In this work, we present a noise-resisting autoencoder, which is the result of a rigorous experiment on different noise types, including less conventional ones, noise levels, and other key hyper parameters. In this study, we used ANOVA and HSD statistical methods, which offered a solid and interpretable basis for a multi-layered, evidence-based understanding of how each hyper parameter shapes the model’s behavior, while providing practical guidance for building more reliable and noise-resistant autoencoder-based intrusion detection systems. Our model was tested on the NSL-KDD achieving an accuracy of 91.64% outperforming state-of-the-art semi-supervised autoencoders models.

Edge computing is transforming data processing by enabling real-time analytics close to data sources. However, this paradigm introduces significant privacy risks due to challenges in complying with diverse regional laws and accurately capturing users' privacy preferences, especially in the presence of multiple actors such as edge entities and third-party providers like cloud services. These challenges result in privacy violations that undermine trust and hinder the adoption of edge-based solutions. This paper identifies critical gaps in ensuring decentralized edge architectures adhere to legal requirements while addressing poorly defined privacy preferences. To address these issues, we propose a conceptual generative AI-driven framework to classify user preferences, formalize privacy policies for all actors, and dynamically align them with local regulations, making compliance detection easier. Through these contributions, this work identifies research opportunities while adhering to privacy by design principles in a conceptual framework to reduce privacy violations and enhance user trust.

In the realm of decentralized applications, smart contracts play a pivotal role in managing an extensive array of digital assets within blockchain networks. Ensuring the security of these digital assets hinges upon the adept detection of vulnerabilities present within smart contracts. Extensive research efforts have scrutinized and elucidated numerous smart contract vulnerabilities. However, certain vulnerabilities, including signature malleability, hash collision, and inconsequential code segments, remain relatively unexplored and devoid of dedicated detection tools. In response to this research gap, this paper addresses these three previously understudied vulnerabilities. We contribute to the field by creating a labeled dataset comprising vulnerable smart contracts. This dataset serves as a valuable resource for further scientific inquiries, enabling the testing and validation of various detection frameworks. Additionally, we present SmartSentry a static vulnerability detection framework capable of identifying these vulnerabilities. Using both dataflow and control flow analysis, our framework exhibits exceptional performance, successfully identifying labeled vulnerabilities and real-world vulnerabilities within production smart contracts with speed and efficiency. These efforts collectively enhance our understanding of smart contract vulnerabilities and contribute to the broader advancement of blockchain security.

Smart contracts are essential for managing digital assets in blockchain networks, highlighting the need for effective security measures. This paper introduces SmartLLMSentry, a novel framework that leverages large language models (LLMs), specifically ChatGPT with in-context training, to advance smart contract vulnerability detection. Traditional rule-based frameworks have limitations in integrating new detection rules efficiently. In contrast, SmartLLMSentry utilizes LLMs to streamline this process. We created a specialized dataset of five randomly selected vulnerabilities for model training and evaluation. Our results show an exact match accuracy of 91.1% with sufficient data, although GPT-4 demonstrated reduced performance compared to GPT-3 in rule generation. This study illustrates that SmartLLMSentry significantly enhances the speed and accuracy of vulnerability detection through LLM-driven rule integration, offering a new approach to improving Blockchain security and addressing previously underexplored vulnerabilities in smart contracts.

The rapid development of the Internet of Medical Things (IoMT) technology has resulted in various advances in the smart healthcare field; it improves healthcare systems to offer more complicated real-time services and provides an efficient patient motioning system. However, despite the brilliant side of IoMT, several concerns continue to undercut its adoption. In fact, collecting, transmitting, storing, and using data in IoMT applications raises issues regarding privacy and data protection, especially with the multitude of stakeholders involved during the whole data life cycle. Motivated from these facts, this article is devoted to perform a Systematic Literature Review (SLR) of privacy-preserving solutions used in the smart healthcare ecosystem. The recent research papers disseminated between 2017 and 2021 are selected from multiple databases and a standardized SLR method is conducted. A total of 100 papers were reviewed and a critical analysis was conducted on the selected papers. Moreover, this review study attempts to highlight the limitation of the current approaches and aims to find possible solutions to them. Thus, a detailed analysis was carried out on the selected papers in terms of the privacy techniques they deployed, the data life cycle phase they addressed, the stakeholders needs they met, and the privacy principles they covered according to privacy laws and regulations. Finally, we summarize our results showing privacy-preserving trends and identifying recommendations to involve privacy principles coverage in smart healthcare applications.

Nowadays, the adoption of Internet of Things (IoT) technology worldwide is accelerating the digital transformation of healthcare industry. In this context, smart healthcare (s-healthcare) solutions are ensuring better and innovative opportunities for healthcare providers to improve patients’ care. However, these solutions raise also new challenges in terms of security and privacy due to the diversity of stakeholders, the centralized data management, and the resulting lack of trustworthiness, accountability, and control. In this paper, we propose an end-to-end Blockchain-based and privacy-preserving framework called SmartMedChain for data sharing in s-healthcare environment. The Blockchain is built on Hyperledger Fabric and stores encrypted health data by using the InterPlanetary File System (IPFS), a distributed data storage solution with high resiliency and scalability. Indeed, compared to other propositions and based on the concept of smart contracts, our solution combines both data access control and data usage auditing measures for both Medical IoT data and Electronic Health Records (EHRs) generated by s-healthcare services. In addition, s-healthcare stakeholders can be held accountable by introducing an innovative Privacy Agreement Management scheme that monitors the execution of the service in respect of patient preferences and in accordance with relevant privacy laws. Security analysis and experimental results show that the proposed SmartMedChain is feasible and efficient for s-healthcare environments.