Research
Research Projects
Explore cutting-edge research projects, scientific publications, ongoing discoveries, and indexed publications in Artificial Intelligence and Internet of Things
Defending Agentic LLM Systems against Prompt Injection and Tool Abuse
Build an evaluation framework and programmable privilege-control mechanisms to reduce the impact of prompt injection and tool abuse in LLM-based agent...
Detection of AI-Generated Social Engineering in Code-Switched Darija-French Communications
Investigate the detectability of AI-generated phishing and social-engineering messages in communications that mix Moroccan Darija, French, and Modern...
Privacy-Preserving Collaborative Threat Intelligence with Graph Neural Networks on Attack Graphs
Enable multiple organizations to collaboratively learn campaign-level attack patterns from provenance graphs without exposing internal topology or sen...
Fairness-Aware Federated Domain Generalization for Multi-Center Medical Imaging in Low-Resource Hospitals
Investigate how a medical-imaging model trained collaboratively across unequally equipped hospitals can remain accurate and fair for under-resourced s...
Guideline-Grounded Clinical Language Models with Calibrated Abstention for Primary Care Triage
Design and evaluate a primary-care triage assistant that answers only when the relevant clinical recommendation can be retrieved and that explicitly q...
Causal Machine Learning for Heterogeneous Treatment Effects from Routine Hospital Records
Estimate which patient subgroups may benefit from a treatment strategy using routine observational hospital data, with explicit sensitivity analysis t...
Synthetic Data Generation and Privacy Auditing for Cross-Border Medical Model Sharing
Assess whether synthetic medical data can replace direct sharing of real patient data by jointly auditing clinical utility and effective re-identifica...
Few-Shot Vision-Language Inspection with Verifiable Explanations on Production Lines
Detect surface defects from very few labeled examples using vision-language models while ensuring that generated explanations are spatially consistent...
Cross-Machine Transfer of Time-Series Foundation Models for Remaining Useful Life Estimation
Evaluate whether representations learned by time-series foundation models can support remaining useful life estimation for equipment with little or no...