Explore the programs and courses offered by PhD in Computer Science specializing in Networks and Distributed Systems
Browse Programs Admission InformationThe doctoral training program in computer science, offered by the Faculty of New Information and Communication Technologies at the University of Constantine 2 Abdelhamid Mehri, aims to train a new generation of highly qualified researchers capable of innovating and addressing national and global challenges. Aligned with national strategic priorities—such as citizen health, energy security, and food security—the program adopts a multidisciplinary approach focusing on artificial intelligence, natural language processing (NLP), machine learning, deep learning, cybersecurity, ambient intelligence, and nanotechnologies.
Supported by renowned research laboratories like TAMAYOUZ MISC, LIRE, and LISIA, and in partnership with national socio-economic stakeholders, the program aims to train 20 doctoral candidates capable of conducting high-level applied and theoretical research, while promoting innovation, interdisciplinary collaboration, and societal impact.
The first year of the doctoral program includes a set of fundamental courses spread over two semesters, aimed at strengthening the scientific, technical, and methodological skills of doctoral candidates. These courses cover artificial intelligence, advanced computer systems, cybersecurity, big data processing, and the foundations of scientific research.
Doctoral candidates also participate in mandatory seminars on research methodology, innovative project management, scientific communication, and ethical issues related to technology. Specialized workshops and optional seminars are offered to allow students to tailor their training path according to their research areas.
Title: A framework for securing Bolckchain smart contracts in distributed Applications
Description:
Nowadays, Blockchain technology has attracted significant attention from academia and industry. Ethereum, which uses blockchain technology, is a distributed computing platform and operating system. Smart contracts are small programs deployed to the Ethereum blockchain for execution. Errors in smart contracts will lead to huge losses. While testing is considered as the de facto standard for verifying the correctness of smart contracts in software development, Formal verification can provide a reliable guarantee for the security of blockchain smart contracts because they are difficult to modify once deployed, and any flaws could result in substantial financial losses. Therefore, formal verification is necessary.
The objective of this thesis is to explore the use of formal verification to deal with the five kinds of security issues (i.e. integer overflow, the function specification issue, the invariant issue, the authority control issue, and the behavior of the specific function) in the blockchain smart contracts.
Furthermore, we present a specific formal verification method for each of these five types of security issues. Second, we establish a formal verification framework to examine the correctness of smart contracts. We propose to model the blockchain smart contracts using UML diagrams, the using model driven method we transform the models into Solidity programs. Then, we formally verify the Solidity code using a formal method that will be chosen. We plan to apply our framework on smart contract-based traceability model that tracks and authenticates Algerian dates throughout the supply chain. A study on the impact of using blockchain to improve consumer confidence and strengthen the position of Algerian dates in international markets. A prototype demonstrating how producers and exporters can use blockchain technology to guarantee the origin and quality of their products. Recommendations for overcoming technical, economic, and legal barriers to adopting a blockchain solution for the traceability of agricultural products in Algeria.
References:
1. S. So, M. Lee, J. Park, H. Lee, H. Oh, Verismart: A highly precise safety verifier for ethereum smart contracts, in: 2020 IEEE Symposium on Security and Privacy (SP), IEEE, 2020, pp. 1678–1694.
2. P. Antonino, A. Roscoe, Solidifier: bounded model checking solidity using
lazy contract deployment and precise memory modelling, in: Proceedings of the 36th Annual ACM Symposium on Applied Computing, 2021, pp. 1788–1797.
3. Alexandre Mota, Fei Yang, and Cristiano Teixeira. Formally Verifying a Real World Smart Contract. 2023.
Available at. 2307.02325] Formally Verifying a Real World Smart Contract
Thesis project
An approach to securing AI Models Deployed for 6G Networks
Abstract- Artificial Intelligence (AI) will play a pivotal role in shaping the capabilities and performance of 6G networks, enabling them to meet the demands of future communication systems. In fact, AI will enable 6G networks to become more intelligent, adaptive, and resilient, unlocking new opportunities for communication, collaboration, and innovation across various industries and applications. However, as AI models become increasingly pervasive in 6G networks, ensuring their security and resilience against emerging threats becomes paramount.
This thesis aims to explore the challenges and opportunities associated with securing AI models deployed in the context of 6G networks. Through a combination of theoretical analysis, empirical studies, and practical implementations, this research seeks to advance our understanding of how to design, develop, and deploy secure AI models in 6G environments. The thesis investigates various aspects of AI-driven security, including adversarial robustness, privacy preservation, explainability, and trustworthiness, and explores their implications for 6G network architecture and operations. By addressing these challenges and proposing novel solutions, this thesis contributes to the advancement of secure AI deployment in 6G networks and lays the foundation for future research in this critical area.
This thesis aims to provide a comprehensive exploration of the security considerations associated with deploying AI models in 6G networks, offering insights into the design, implementation, and evaluation of secure AI solutions tailored to the unique requirements of next-generation communication systems.
Keywords: 6G Networks, Edge Computing, Artificial Intelligence, Advanced deep learning, adversarial Attacks, Explainability, Privacy and Trust.
Plan and Objectives:
1. Context and Background: Evolution of 6G networks and the role of AI
2. Specification of Challenges: Security challenges in AI deployment for 6G networks
3. Literature Review: Existing approaches to securing AI models in networked environments
4. Contributions: Design and development of new solutions on Secure AI Models for 6G Networks.