Property:OneLineSummary
From ISLAB/CAISR
Jump to navigationJump to searchS
Secure Hardware Accelerators for Machine Learning: Design, Evaluation, and Mitigation of Vulnerabilities +
This master's project focuses on investigating the security of hardware accelerators designed for machine learning +
Design a decentralized and lightweight key management scheme that ensures secure communication even under network partitions. +
investigating the HW/SW design of light-weight authentication for IoAV +
Securing Multi-Processor System-on-Chips: Assessing Vulnerabilities to Hardware Trojans Through Thermal Profiles +
This master's thesis project is dedicated to conducting a comprehensive security assessment of modern multi-processor System-on-Chips (MPSoCs) equipped with multiple thermal sensors. +
Discover and quantify timing side-channels and model-fingerprinting risks in multi-tenant CiM accelerators using open simulators and a custom runtime +
Potential security vulnerabilities of IIoTs platform connectivity protocols, such as CoAP and MQTT will be studied. +
Segment Routing based on Geographic Checkpoints: +
Segment-based coordination of Congestion Control +
Segmentation and object identification in warehouse environments using machine learning +
Finding boundaries of homogeneous regions in shoeprint images +
In this project we intend to develop an adaptive system that can adapt itself --based on different context-- at providing service to conditional preference of users which change over time. +
Semantic Analysis of 2D Maps With a Metric-Topological Approach. +
Semi-supervised deep learning model to optimally charge and discharge the batteries of electric cars and balance distribution of electrical energy in the power grid +
A semi-supervised deep learning model will be developed to optimally charge and discharge the batteries of electric cars while they are connected to the power grid. (In collaboration with Sam Houston State University (USA)). +
Sensitivity‑Aware Hardening and Run‑Time Detection of Stealthy Weight‑Drift Trojans in ML Accelerators +
design and evaluate sensitivity-aware defences that detect and mitigate stealthy, gradual weight-drift Trojans in FPGA-based ML accelerators +
Sensor fusion and machine learning for drone detection and classification +
Service Centric Mobility Management in LEO Constellations +
Forecasting the electricity consumption based on historical usage by using smart meter data +
Automatic Simplification of Scientific Texts +
Integrate crowd simulation into a mixed-reality platform for development and testing of advanced automotive safety systems. +
Develop a simulation-based study of cyber attacks and countermeasures in CybORG, comparing baseline scripted defenses with reinforcement learning–based adaptive defenders to identify effective strategies for protecting networked systems. +
