Selected Research Publications - Under Construction

2025

NoirAgent: The World's First Scalable, Private, and Secure AI Agent. PCT Application. [Upcoming]
Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs). Mahmoud Nazzal, Issa Khalil, Abdallah Khreishah, NhatHai Phan. PCT Application.
A Client-level Assessment of Collaborative Backdoor Poisoning in Non-IID Federated Learning. Phung Lai, Guanxiong Liu, NhatHai Phan, Issa Khalil, Abdallah Khreishah, and Xintao Wu. The 45th IEEE International Conference on Distributed Computing Systems (IEEE ICDCS) 2025.
Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs). Apurv Verma, Satyapriya Krishna, Sebastian Gehrmann, Madhavan Seshadri, Anu Pradhan, John A. Doucette, David Rabinowitz, Leslie Barrett, Tom Ault, NhatHai Phan. Transactions on Machine Learning Research (TMLR), 2025.

SGCode: A Flexible Prompt-Optimizing System for Secure Generation of Code (Demo System). Khiem Ton, Nhi Nguyen, Mahmoud Nazzal, Abdallah Khreishah, Cristian Borcea, NhatHai Phan, Ruoming Jin, Issa Khalil, Yelong Shen. The 31st ACM Conference on Computer and Communications Security (ACM CCS'24).
PromSec: Prompt Optimization for Secure Generation of Functional Source Code with Large Language Models (LLMs). Mahmoud Nazzal, Issa Khalil, Abdallah Khreishah, NhatHai Phan. The 31st ACM Conference on Computer and Communications Security (ACM CCS'24).

XRand: Differentially Private Defense against Explanation-Guided Attacks. Truc Nguyen*, Phung Lai*, NhatHai Phan, and My T. Thai. AAAI Conference on Artificial Intelligence (AAAI 2023). (* equal contributions) [AAAI 2023 Distinguished Paper Award]
Active Membership Inference Attack under Local Differential Privacy in Federated Learning. Truc Nguyen, Phung Lai, Khang Tran, NhatHai Phan, and My T. Thai. The 26th International Conference on Artificial Intelligence and Statistics (AISTATS 2023).