Research Projects
Current funded research appears first, followed by selected research projects and their associated publications, artifacts, or demonstrations.
Current Funded Research
Intelligent Framework for Securing IoT Systems in Critical Infrastructure
Research challenge: Critical-infrastructure IoT devices often use custom firmware that is difficult to validate at scale, creating risks involving functional correctness, software vulnerabilities, and hardware incompatibility.
Project direction: The project develops a hardware-aware LLM verification framework for IoT firmware. The funded project description organizes the approach across input-level optimization, representation-level graph/semantic reasoning, and system-level integration with external security scanners and hardware simulators.
Securing Mobile Agentic AI Systems: Systematic Risk Analysis and Defense Against Confused Deputy Behavior
Research challenge: Mobile LLM agents interact with applications, notifications, third-party SDKs, and privileged system resources. These interactions can expose agents to adversarial inputs and confused-deputy behavior across application boundaries.
Project direction: The funded project studies automated generation of realistic adversarial scenarios, principled measurement of agent misbehavior, and graph-based runtime defenses for detecting and mitigating confused-deputy behavior.
Selected Research Projects
PromSec / SGCode: Prompt Optimization for Secure Generation of Functional Source Code
Research challenge: LLM-generated code can be functional while still containing security vulnerabilities.
Approach: PromSec develops prompt optimization for secure and functional code generation; SGCode demonstrates a flexible prompt-optimizing system built around this research direction.
Associated paper(s): “PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs),” ACM CCS 2024; “Demo: SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code,” ACM CCS 2024.
MintA: Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detection
Research challenge: Graph-based malicious-domain detectors can be targeted by coordinated changes to multiple attacker-controlled entities.
Approach: MintA studies black-box multi-instance evasion against GNN-based malicious-domain detection and evaluates the attack against defenses including outlier detection and graph purification.
Associated paper: “Multi-Instance Adversarial Attack on GNN-Based Malicious Domain Detection,” IEEE Symposium on Security and Privacy (S&P) 2024.
ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks
Research challenge: Deepfake detection requires methods that can leverage complementary visual and semantic evidence while remaining robust across manipulation types.
Approach: ViGText combines vision-language model explanations with graph neural networks for deepfake image detection.
Associated paper: “ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks,” 33rd Network and Distributed System Security Symposium (NDSS 2026).
FedChip and SA-DS: LLM-Aided AI Accelerator Design
Research direction: Explore LLM-based methods and datasets for artificial-intelligence accelerator design generation.
Selected outcomes: FedChip studies federated LLMs for AI accelerator chip design; SA-DS provides a dataset for LLM-driven AI accelerator design generation.
Associated paper(s): “FedChip: Federated LLM for Artificial Intelligence Accelerator Chip Design,” IEEE ICLAD 2025; “SA-DS: A Dataset for Large Language Model-Driven AI Accelerator Design Generation,” IEEE ISCAS 2025.
STING: Stealthy Backdoor Attack on GNN-Based Malicious Domain Detection
Research direction: Study stealthy backdoor attacks against graph-neural-network-based malicious-domain detection through DNS perturbations.
Associated paper: “STING: A Stealthy Backdoor Attack on GNN-Based Malicious Domain Detection via DNS Perturbations,” IEEE Open Journal of the Communications Society, vol. 6, pp. 7823–7841, 2025.
Semi-Decentralized Inference in Heterogeneous GNNs for Traffic Demand Forecasting
Research direction: Edge-computing inference with heterogeneous graph neural networks for traffic demand forecasting.
Associated paper: “Semi-Decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approach,” IEEE Transactions on Vehicular Technology, vol. 73, no. 12, pp. 19400–19416, 2024.