Team – Lacsii Cybersecurity

Prof. Anderson Avila

Assistant Professor at INRS-EMT, working in the INRS-UQO Joint Research Unit in Cybersecurity. His research background is on machine learning and signal processing applied to natural language processing. During his PhD, Dr. Avila worked on the development of new models for speech quality assessment and on the robustness of voice biometrics.

Before he was a researcher scientist in natural language and speech processing, working on projects related to model compression, low-latency and robustness of spoken language understanding.

Current Lab Members

Postdoctoral Fellows

Mahdi Abderrahim

Short bio: He holds a Ph.D. in Computer Science and Engineering from Hamad Bin Khalifa University. He is currently a postdoctoral researcher at UMR INRS-UQO. His research focuses on privacy-preserving and secure machine learning systems, with an emphasis on applied cryptography, federated learning, and cybersecurity. Specifically, he investigates how to design efficient and trustworthy protocols for distributed AI systems, protect machine learning models against privacy attacks, and enhance the security of emerging applications such as smart grids, networked systems, and privacy-preserving large language models.

Research topic: Privacy-preserving and secure machine learning

PhD Students

Nasim Soltani

Short bio: She holds B.Sc. and M.Sc. in Computer Engineering from Payam Noor University (PNU) and Allameh Naeini Higher Education Institute, respectively. She is currently a Ph.D. candidate at INRS-EMT. Her research focuses on advancing the robustness and collaborative fairness of federated learning systems. Specifically, she investigates how to design resilient models that can operate effectively under diverse and heterogeneous environments while ensuring equitable outcomes across participating clients. Additionally, she explores strategies to mitigate vulnerabilities in distributed learning and enhance collaboration fairness, contributing to the development of trustworthy and AI.

Research topic: Collaborative fairness and robustness in Federated Learning

Fabricio Steinle Amoroso

Short bio: BSc and MSc degrees in Computer Science from São Paulo State University (UNESP), Brazil. Conducted research at the Laboratory of Applied Security and Networks (LARS), focusing on cybersecurity applications of deep learning. Research interests include deepfake detection, intrusion detection systems, and intelligent security mechanisms for computer networks. Currently pursuing a PhD in Telecommunications at INRS-EMT.

Research topic: Efficient knowledge distillation for speech pretrained models

Master Students

Moetaz Doghmane

Short bio: I am currently pursuing a Master’s degree in Cybersecurity at the Institut National de la Recherche Scientifique (INRS), within the Unité Mixte de Recherche INRS–UQO. My research interests include misinformation detection, machine learning, artificial intelligence, and software engineering. Prior to joining the program, I obtained a Bachelor’s degree in Computer Engineering from ESPRIT School of Engineering and Technology (Tunisia).

Research topic: Uncertainty in LLM.

Muhammad Saadan

Short bio: Muhammad Saadan holds a Bachelor's degree in Software Engineering from the National University of Sciences and Technology (NUST). During his studies, he gained industry and research experience through internships as a Network Security Intern at NADRA and a Deep Learning Intern at the ONT Lab, followed by the Mitacs Globalink Research Internship at INRS-UQO. He is currently pursuing his Master's, with his research focused on self-supervised speech pre-training, federated learning, knowledge distillation, and agentic AI.

Research topic: Self-Supervised Speech Pre-training and Federated Learning

Yassin Sadfi

Short bio: Yassin holds an Engineering degree in Infotronics (Computer Science & Embedded Systems ) from ENICarthage and is currently pursuing a Master's degree in Artificial Intelligence for Cybersecurity at INRS. His background includes machine learning, natural language processing, and large language models, with experience in; developing AI agents , Retrieval-Augmented Generation (RAG) systems, and prompt engineering. Currently, his research focuses on enhancing intent recognition in Large Language Models to improve their reliability and robustness in real-world applications.

Research topic: Enhancing intent recognition and verification in Large Language Models (LLMs).