- Ethics and Social Impacts of AI
- Network Security and Intrusion Detection
- Advanced Malware Detection Techniques
- Adversarial Robustness in Machine Learning
- Anomaly Detection Techniques and Applications
- Artificial Intelligence in Healthcare and Education
- Cloud Computing and Resource Management
- Privacy-Preserving Technologies in Data
- Quantum Computing Algorithms and Architecture
- Artificial Immune Systems Applications
- Internet Traffic Analysis and Secure E-voting
- IoT and Edge/Fog Computing
- Topological and Geometric Data Analysis
- Information and Cyber Security
- Software Engineering Research
- Security and Verification in Computing
- Advanced Data Processing Techniques
- Quantum Information and Cryptography
- Smart Grid Security and Resilience
- Software Reliability and Analysis Research
- Machine Learning and Data Classification
- Explainable Artificial Intelligence (XAI)
- Ethics in Clinical Research
- Advanced Data Storage Technologies
- Formal Methods in Verification
Polytechnique Montréal
2022
Université de Sherbrooke
2018-2020
Telecom SudParis
2018-2019
Centre National de la Recherche Scientifique
2018-2019
Département d'Informatique
2018-2019
Orange (France)
2018
Nowadays, network technologies are essential for transferring and storing various information of users, companies, industries. However, the growth transfer rate expands attack surface, offering a rich environment to intruders. Intrusion detection systems (IDSs) widespread able passively or actively control intrusive activities in defined host perimeter. Recently, different IDSs have been proposed by integrating techniques, generic adapted specific domain nature attacks operating on. The...
Artificial Intelligence (AI) is transforming our daily life with many applications in healthcare, space exploration, banking, and finance. This rapid progress AI has brought increasing attention to the potential impacts of technologies on society, ethically questionable consequences. In recent years, several ethical principles have been released by governments, national organizations, international organizations. These outline high-level precepts guide development, deployment, governance AI....
Machine learning is a field of artificial intelligence (AI) that becoming essential for several critical systems, making it good target threat actors. Threat actors exploit different Tactics, Techniques, and Procedures (TTPs) against the confidentiality, integrity, availability Learning (ML) systems. During ML cycle, they adversarial TTPs to poison data fool ML-based In recent years, multiple security practices have been proposed traditional systems but are not enough cope with nature this...
Integrating ethical practices into the AI development process for artificial intelligence (AI) is essential to ensure safe, fair, and responsible operation. ethics involves applying principles entire life cycle of systems. This mitigate potential risks harms associated with AI, such as algorithm biases. To achieve this goal, design patterns (RDPs) are critical Machine Learning (ML) pipelines guarantee fair outcomes. In paper, we propose a comprehensive framework incorporating RDPs ML Our...
Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning a field AI that enables to learn from data make decisions on new based models achieve given goal. The stochastic nature makes verification validation tasks challenging. Moreover, there are intrinsic biaises reproductibility bias, selection bias (e.g., races, genders, color), reporting (i.e., results...
Recent advancements in quantum computing, exemplified by IBM's computers, underscore the importance of software. Differing fundamentally from classical programming, programming's probabilistic state and inherent error-prone nature due to instabilities pose unique challenges. This study investigates bug characteristics software projects inform effective testing debugging strategies. We analyzed reports 125 on GitHub found them more costly rectify compared Key areas where bugs manifested...
Algebraic State-Transition Diagrams (ASTDs) are extensions of common automata and statecharts that can be combined with process algebra operators like sequence, choice, guard quantified synchronization. They were previously introduced for the graphical representation, specification proof information systems. In an attempt to use ASTDs specify cyber-attack detection, we have identified a number missing features in ASTDs. This paper extends ASTD notation state variables (attributes), actions...
Recent advances in deep learning (dl) have led to the release of several dl software libraries such as pytorch, Caffe, and TensorFlow, order assist machine (ml) practitioners developing deploying state-of-the-art neural networks (DNN), but they are not able properly cope with limitations testing or data processing. In this paper, we present a qualitative quantitative analysis most frequent combination, distribution library dependencies across ml workflow, formulate set recommendations (i)...
Artificial Intelligence (AI) is transforming our daily life with several applications in healthcare, space exploration, banking and finance. These rapid progresses AI have brought increasing attention to the potential impacts of technologies on society, ethically questionable consequences. In recent years, ethical principles been released by governments, national international organisations. outline high-level precepts guide development, deployment, governance AI. However, abstract nature,...
Increasingly, malwares are becoming complex and they spreading on networks targeting different infrastructures personal-end devices to collect, modify, destroy victim information. Malware behaviors polymorphic, metamorphic, persistent, able hide bypass detectors adapt new environments, even leverage machine learning techniques better damage targets. Thus, it makes them difficult analyze detect with traditional endpoint detection response, intrusion prevention systems. To defend against...
With the advance in quantum computing recent years, software becomes vital for exploring full potential of systems. Quantum programming is different from classical programming, example, state a program probabilistic nature, and computer error-prone due to instability mechanisms. Therefore, characteristics bugs projects may be very that projects. This work aims understand projects, order provide insights help devise effective testing debugging To achieve this goal, we conduct an empirical...