Active Grant | Yao Zheng@UHM

DOE Genesis Mission: STRATOS: Security and Trust Runtime Architecture for Time-critical Operational Science

Mon, 17 Aug 2026 10:10:00 -1000

Executive Summary

STRATOS develops a cloud-native, model-agnostic security middleware for protecting AI models used in time-critical scientific and energy-system operations. AI is increasingly embedded in workflows such as grid forecasting, contingency analysis, and operational decision making, creating new risks from adversarial perturbations, inference-time evasion, and backdoor attacks that may remain physically plausible while corrupting model outputs. STRATOS addresses this problem through a physics-grounded DevSecOps architecture that continuously evaluates inference streams, computes certified trust scores, and distinguishes malicious manipulation from legitimate operational variability without requiring modification of the protected model.

The project combines physics-constrained adversarial emulation, imbalance-resilient certified detection, and a multi-tier runtime mitigation pipeline that includes targeted input purification, Control Barrier Function-based graceful degradation, and quarantine or rollback of compromised data and models. The Phase I system will be evaluated across the University of Hawaiʻi at Mānoa campus microgrid and Argonne National Laboratory’s Controller-Hardware-in-the-Loop platform, targeting at least 90% certified detection, no more than 5% false positives, at least 95% interception of synthesized adversarial payloads, and end-to-end latency of 20 ms or less. The longer-term goal is to transition STRATOS toward a federated security architecture for trustworthy AI across DOE scientific computing and critical-infrastructure environments.

CyberAI Innovation: Securing Artificial Intelligence Agents: A Scenario-Based Educational Platform for Future Cybersecurity Professionals

Sat, 15 Aug 2026 15:29:00 -1000

Executive Summary

AI agents that autonomously browse the web, manage email, execute code, and query databases are being deployed across federal agencies at accelerating pace. These agents create a qualitatively new attack surface: a poisoned email can cause an agent to exfiltrate files; a malicious code comment can redirect an execution pipeline; a hidden webpage instruction can hijack a browsing session. Yet cybersecurity education has not kept pace. Existing AI security tools (Lakera Gandalf, OWASP LLM labs, CTF competitions) teach only chatbot-level prompt injection, a single-turn, text-only model that does not prepare students for agent-mediated threats involving tool access, autonomous action, and multi-step reasoning chains.

This project develops AgentSec, a scenario-based educational platform that teaches undergraduate cybersecurity students to identify, exploit, and defend against threats unique to autonomous AI agents, organized into three thrusts. Thrust 1 creates the educational framework, where a trust boundary taxonomy organizes agent vulnerabilities into three progressive categories, i.e., data ingestion, tool-action, and reasoning chain boundaries. This gives students a transferable mental model. Based on the taxonomy, we design a three-module curriculum with six organization-contextualized scenarios, red-team/blue-team experiential learning cycles, and a configurable difficulty framework. Thrust 2 builds the educational technology, where we develop sandboxed environments to enable students’ interaction with real LLM-powered agents with controlled tool access, a layered assessment system with an AI tutoring agent, an instructor analytics dashboard, and a scenario authoring toolkit for community-contributed content. Thrust 3 evaluates impact through a quasi-experimental study, assessing platform quality, student learning, and workforce placement into government and industry CyberAI roles. All code will be open-source, self-hostable via Docker Compose with open-weight models, and released through CLARK for nationwide adoption.

NVIDIA Academic Grant Program: OmniPort: Real-Time Semantic Digital Twins via ISAC and AI-RAN for Smart Ports

Sat, 15 Aug 2026 15:29:00 -1000

Executive Summary

OmniPort develops a real-time intelligent wireless and digital-twin platform for safer and more efficient autonomous operations in container ports. Ports are particularly challenging environments for robots because stacked metal containers obstruct GPS and line-of-sight sensors while producing strong wireless multipath. Instead of treating these reflections solely as interference, OmniPort uses integrated sensing and communication (ISAC) to extract information from routine robot uplink signals, enabling around-corner hazard detection and GPS-free robot localization. An AI-RAN then combines these sensing results with robot mobility and network telemetry to predict wireless conditions, dynamically allocate network resources, and maintain low-latency communication for safety-critical operations.

The project integrates these capabilities into an uncertainty-aware semantic digital twin that represents container geometry, robot movement, hazards, and wireless connectivity in real time. Rather than continuously transmitting camera video, operators can supervise robot fleets through a privacy-preserving VR environment generated from this semantic information, with warnings for collision risks, connectivity degradation, and emerging hazards. The platform uses four on-premises NVIDIA RTX PRO 6000 GPUs to support concurrent ISAC processing, AI-RAN control, NVIDIA Isaac Sim/Cosmos-based digital-twin reasoning, and Omniverse VR visualization, targeting an end-to-end control latency below 50 ms. The resulting technologies, software, and datasets are intended to provide a foundation for intelligent robotic operations in Hawaiʻi’s ports and other complex industrial environments.

Drone-Mounted mmWave Harmonic Radar for Invasive Insect Monitoring

Fri, 07 Nov 2025 00:00:00 -1000

Executive Summary

This project develops an innovative drone-mounted millimeter-wave (mmWave) harmonic radar system for tracking invasive pest insects in Hawai‘i. The technology targets destructive species such as the coconut rhinoceros beetle and melon fly, aiming to improve early detection, optimize control strategies, and protect the islands’ ecosystems and agriculture.

Traditional harmonic radar systems are limited to short ranges and heavy transponders. Our approach integrates 12 GHz/24 GHz phased-array beamforming, miniaturized Nitinol-based transponders, and multi-drone coordination for long-range, real-time tracking of small, fast-moving insects—achieving high precision with minimal behavioral impact.

Research Objectives

Goal: Build and validate a UAV-mounted harmonic radar network for aerial tracking of invasive insects across complex Hawaiian landscapes.

Task 1 – mmWave Beamsteering Harmonic Transceiver

Design a compact 12 GHz phased-array transmitter using COTS modules and a heterodyne architecture for coherent beamforming.

Operates at 12/24 GHz ISM bands
Achieves >10 m range with lightweight, steerable arrays
Enables UAV integration for agile tracking

Task 2 – Ultralight Harmonic Tag

Develop a miniaturized 24 GHz transponder using a hollow bowtie antenna made of shape-memory alloy (Nitinol) and a Schottky diode for harmonic generation.

Tag weight < 1 mg for compatibility with small insects
Structural resilience through Nitinol’s superelasticity
Broadband harmonic reflection optimized for 12→24 GHz doubling

Task 3 – Multi-Drone Localization Network

Implement a distributed multistatic radar system using one TX and multiple RX drones for real-time localization.

Uses synchronized bistatic ranging and multilateration
Integrates GPS time sync and low-latency communications
Coordinates drone formations for continuous insect tracking

Broader Impacts

This system aligns with HISC priorities for early detection and rapid response (Priority 1) and technological innovation for pest management (Priority 2). It promotes cross-disciplinary collaboration among engineers, biologists, and agricultural scientists to create deployable surveillance tools for invasive species control.
Potential benefits include:

Reduced pesticide dependence through precise targeting
Enhanced monitoring of remote or forested regions
Scalable open-source framework for ecological sensing

Team

PI: Dr. Yao Zheng – mmWave radar, phased array, RF sensing
Co-PI: Dr. Haofan Cai – RFID and low-power tag design
Co-PI: Dr. Daniel Jenkins – UAV systems, autonomous sensing, precision agriculture

Collaborators include USDA-PBARC and NIWC Pacific for field validation and data integration.

Timeline (Dec 2025 – Nov 2026)

Phase	Period	Milestone	Lead
Phase I	Months 1–3	Frequency translator upgrade and system specification	UHM ECE
Phase II	Months 4–6	Phased-array prototype and beamforming validation	UHM ECE
Phase III	Months 7–9	Harmonic tag fabrication and field characterization	UHM ECE
Phase IV	Months 10–12	Multi-drone localization demo and final reporting	UHM ECE

Expected Deliverables

Functional 12/24 GHz drone-mounted harmonic radar prototype
Miniaturized Nitinol-based insect tags (< 1 mg)
Validated multi-drone localization system (> 100 m effective range)
Technical documentation and open-source dataset for future HISC programs

📡 Project Lead:
🏛️ Institution: University of Hawai‘i at Mānoa – College of Engineering
🌺 Supported by: Hawai‘i Invasive Species Council (HISC) 2026–2027