Preventing Cybersecurity Threats in a Highly Malicious Distributed Machine Learning based IoT Environment
Project aim: Detect data poisoning and model poisoning attacks and guarantee convergence by tackling malicious participants within an FL environment.
Towards a Lightweight and Scalable Blockchain Framework for Resource-Constrained Federated Learning (FL) Environment
Project aim: Develop a lightweight and scalable blockchain framework tailoring an effective blockchain consensus mechanism to circumvent malicious activities. The project has broader prospects in security, storage, and incentive mechanism.
Project aim:
(1) Capture interdependence among human-centered multi-layer critical infrastructures;
(2) Perform data analytics and enable interdependent decision making; and
(3) Develop efficient solutions that are capable of finding globally optimum solutions.
Project aim:
(1) Facilitate training of each agent in a distributed fashion;
(2) Resource optimization in exchanging knowledge; and
(3) Minimal communication overhead during training.
We propose a distributed sensing approach that is capable to identify a device using token, can activate distributed end-user devices to send data to the cloud whenever it requires and store data in the cloud server maintaining proper format. This approach enables remote data collection leveraging available end-user devices and reduces the cost of installing new sensors for autonomous IoT applications.
Related Publications:
Ahmed Imteaj, M.Hadi Amini, "Distributed Sensing Using Smart End-user Devices: Pathway to Federated Learning for Autonomous IoT", 2019 IEEE Conference on Computational Science & Computational Intelligence, 2019. (Best Paper Award Winner) [FIU SCIS] [UGS News] [FIU News]
This research aimed to address the blockchain management problem by designing a lightweight blockchain framework, coined as Sensor-Chain, for mobility-centric IoT without relying on a fixed infrastructure of edge devices. We show that breaking down a traditional global blockchain into smaller local blockchains in the spatial domain and limiting their size through a temporal constraint will allow us to design scalable blockchain for mobile IoT systems.
Related Publications:
Abdur R. Shahid, Niki Pissinou, Sheila Alemany, Ahmed Imteaj, Kia Makki, and Laurent Njilla. "Quantifying Location Privacy in Permissioned Blockchain-based Internet of Things (IoT)". In 2019 EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services (MobiQuitous).
In this project, we propose a novel location privacy-preserving approach, called KLAP, based on Since early March 2020, solid lab has proactively contributed to data analytics, network science, risk management, and machine learning research for analysis, prediction, and exploration of COVID-19. In addition to our predictive dashboard that leverages data science to forecast the number of cases and provide a spatiotemporal visualization, we are actively working with network scientists, civil engineering, economists, and operational research collaborators on various aspects of COVID-19 related research.
Related Publications:
1- Spatiotemporal predictive dashboard to forecast and visualize COVID-19 cases using data analytics
[1] M. Hyman, A. Imteaj, & Amini, M.H. (2020). Data Analytics for COVID-19 Prediction; Available from: https://public.tableau.com/profile/solid.lab#!/vizhome/DataAnalyticsforCOVID-19Prediction/Covid-19Dashboard
News Coverage: FIU News, FIU CEC, FIU CEC LinkedIn, FIU SCIS, FIU SCIS LinkedIn
2- Economic Implications of COVID-19 (ongoing collaboration):
[2] M. Hadi Amini, M. Hyman, A. Imteaj, “Efficient Data Analytics For Interdependent Healthcare And Financial Networks: Tale Of Economic Shockwaves Caused By COVID-19”, INFORMS Annual Meeting 2020 session on Modeling Infection Propagation and Designing Surveillance Strategies.
The project aims at supplying water into the farmland by observing the condition of soil, weather and level of water. Through this work, we can monitor any part within a large field, and can also supply water to that particular region.
Related Publications:
Ahmed Imteaj, Tanveer Rahman, Muhammad Kamrul Hossain, and Saika Zaman, "IoT based autonomous percipient irrigation system using raspberry Pi," in proceedings of 19th International Conference on Computer and Information Technology (ICCIT), pp. 563-568. IEEE, 2016.
Ahmed Imteaj, Tanveer Rahman, Mohammed Shamsul Alam, and Touhidul Alam. "Automated Expedient Watering System For Small Plants And Acquaintance About Deficit In Water Supply."