NSF Award # 2610915: "Collaborative Research: CISE MSI: RDP: SaTC: Exploring Cybersecurity and Privacy Enhancement Techniques for AIoT" (Jan. 2025 - Dec. 2027)

This is a jointly project by Yeshiva University, CUNY York College, and Stevens Institute of Technology

Team Members:

Project Mission:

This three-year NSF project advances secure Artificial Internet of Things (AIoT) systems by addressing the data security and privacy risks that emerge when AI runs on IoT devices for low-latency, real-time decision-making. The research investigates AIoT attack-and-defense problems—including data poisoning, federated learning privacy/robustness, and secure computation offloading—supported by development of a joint AIoT testbed. To build sustained capacity, the project establishes cross-department and cross-institution collaborations, including a new Cybersecurity and AI Lab at York College, a summer visiting student research program at Yeshiva University, and a shared AIoT research testbed. The project engages students from underrepresented groups, develops new courses/modules, and disseminates outcomes through workshops, a project website, and peer-reviewed publications and conferences.

Project Activities:

2025 Summer Visiting Program (June 2025):

2025 Seminar (February 2025):

Abstract: AIoT end devices are usually equipped with limited computational resources for real-time inference and learning. In some applications such as drone systems, performing AI tasks on AIoT devices locally not only impacts real-time performance but also consumes significant energy which greatly reduces the on-duty time of the devices. With the emergence of 6G techniques such as open radio access networks (O-RAN), ubiquitous availability of edge computing servers is made possible. This allows AIoT devices to collaborate with nearby edge servers in real time and offload computation-heavy operations pertaining to AI inference and learning to these servers. To realize this AI paradigm, one major challenge in Artificial Intelligent of Things (AIoT) is to appropriately balance efficiency and data privacy as AIoT data will be sent to edge servers.

This talk will discuss several practical techniques toward efficient and secure AI task offloading in edge-assisted AIoTsystems. The first technique is based on a light-weight cryptographic protocol that supports real-time data encryption andcomputation on encrypted data. This technique enables AIoT devices to securely offload AI inference tasks to edge servers without significant computation overhead and communication delay. The second technique employs secure hardware such as trusted execution environment (TEE) to enable offloading of training tasks in zero trust AIoT systems. A real-time learningstate verification mechanism is designed to assure integrity of both AIoT devices and edge servers while preserving data privacy. We implemented these algorithms and protocols on embedded devices such Raspberry Pi and commodity desktop computers and demonstrated the practicality of the proposed designs. 

Publication:

1. Xiaochan Xue, Shucheng Yu, Saurabh Parkar, and Yao Zheng, “ROISD: RIS and O-RAN Assisted Intelligent Sensing for UAV Detection”, 2025 IEEE Annual Congress on Artificial Intelligence of Things (IEEE AIoT), Osaka, Japan, December 3 – 5, 2025. 

2. Srivatanakul, T.; Yu, S.; Kamruzzaman, A.S.; Li, J.; Zhang, D.; Tyrer, E., "WIP: Broadening Participation Through Cross-Institutional and Cross-Disciplinary Research Training and Mentoring in AIoT Cybersecurity for Undergraduate Students", Frontiers in Education Conference, October 11-14, 2026, Paphos, Cyprus. (under submission)