Publications

Patents

• SAFESeal: Certified Watermarking for Large Language Models. Kieu Dang, Phung Lai, NhatHai Phan, Filing Provisional UAlbany Patent 2025.

• Training Language Models and Preserving Privacy. Phung Lai, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Target filling date for Non-provisional US Patent: 21/02/2023. 

• Privacy-Aware Language Models Training. Phung Lai, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Provisional Adobe Patent 2022. 

• Preserving User-Entity Differential Privacy in Natural Language Modeling. Phung Lai, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Non-provisional US Patent 2021 (To be published in Feb 2023).

• User-Entity Differential Privacy in Natural Language Modeling. Phung Lai, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, Nikolaos Barmpalios, Provisional Adobe Patent 2021. 

Publications

2025

• \delta-STEAL: LLM Stealing Attack with Local Differential Privacy. Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen, Ruoming Jin, Abdullah Khreishah. ACML 2025.

• From Black Box to Insight: Explainable AI for Extreme Event Preparedness. Kiana Vu, Ismet Ozer, Phung Lai, Zheng Wu, Thilanka Munasinghe, Jennifer Wei. IEEE BigData workshop 2025.

• AI-Powered Assessment of Wazuh for Obfuscated Threat Detection. Dylan Tarace, Phung Lai, Kieu Dang, Unal Tatar. The Systems and Information Engineering Design Symposium (IEEE SIEDS), 2025.

• A Client-level Assessment of Collaborative Backdoor Poisoning in Non-IID Federated Learning. Phung Lai, Guanxiong Liu, NhatHai Phan, Issa Khalil, Abdallah Khreishah, Xintao Wu. International Conference on Distributed Computing Systems (ICDCS), 2025.

• FedX: Adaptive Model Decomposition and Quantization for IoT Federated Learning. Phung Lai, Xiaopeng Jiang, NhatHai Phan, Cristian Borcea, Khang Tran, An Chen, Vijaya Datta Mayyuri, Ruoming Jin. Annual International Conference on Distributed Computing in Smart Systems and the Internet of Things (DCOSS-IoT), 2025.

• SoK: Are Watermarks in LLMs Ready for Deployment? Kieu Dang, Phung Lai, NhatHai Phan, Yelong Shen, Ruoming Jin, Abdullah Khreishah. My Thai, arXiv preprint arXiv:2506.05594, 2025.

2024

• Navigating Trustworthiness in LLMs: An Examination of Privacy, Security, and Robustness. Kieu Dang, Phung Lai, International Conference on Computational Data and Social Networks, 2024.

• Trustworthiness in Vision-Language Models. Kiana Vu, Phung Lai, International Conference on Computational Data and Social Networks, 2024.

• Assessment of quantum ML applicability for climate actions: comparison of the variational quantum classifier and the quantum support vector classifier with classical ML models. Thilanka Munasinghe, Phung Lai, Jennifer Wei, Jame Hendler, Kim Cornell, IEEE BigData, 2024.

• Xsub: Explanation-driven adversarial attack against blackbox classifiers via feature substitution. Kiana Vu, Phung Lai, Truc Nguyen, IEEE BigData, 2024.

• Book Chapter: Privacy in Federated Learning Natural Language Models. Phung Lai, Ariel C. Pinto, Handbook of Trustworthy Federated Learning, 2024.

• Quantum Leap: Evaluating the Feasibility of Quantum Machine Learning Using NASA Earth Observational Data. Thilanka Munasinghe, Jennifer Wei, Phung Lai, Jame Hendler. NASA Technical Report, 2024.

2023

• How to Backdoor HyperNetwork in Personalized Federated Learning? Phung Lai, Hai Phan, Issa Khalil, Abdallah Khreishah, Xintao Wu. NeurIPS-BUGS 2023. 

• Differential Privacy in HyperNetworks for Personalized Federated Learning. Vaisnavi Nemala, Phung Lai, and Hai Phan. CIKM 2023. Short Paper (acceptance rate: 152/554). 

• Active Membership Inference Attack under Local Differential Privacy in Federated Learning. Truc Nguyen, Phung Lai, Khang Tran, NhatHai Phan, and My T. Thai. AISTATS 2023. 

• XRand: Differentially Private Defense against Explanation-Guided Attacks. Truc Nguyen*, Phung Lai*, NhatHai Phan, and My T. Thai. AAAI 2023. (acceptance rate 19%: 1,721 / 8,777) (*: Co-first author) [Distinguished Paper Award (12 selected/8,777)] 

2022

• User-Entity Differential Privacy in Learning Natural Language Models. Phung Lai, NhatHai Phan, Tong Sun, Rajiv Jain, Franck Dernoncourt, Jiuxiang Gu, and Nikolaos Barmpalios. IEEE BigData 2022. Regular Paper (acceptance rate: 122/633). [Github] [Oral Presentation]

• Lifelong DP: Consistently Bounded Differential Privacy in Lifelong Machine Learning. Phung Lai, Han Hu, NhatHai Phan, Ruoming Jin, My Thai, An Chen. The Conference on Lifelong Learning Agents (CoLLAs 2022), Proceedings of Machine Learning Research (PMLR). (* corresponding author)

• OnML: An Ontology-based Approach for Interpretable Machine Learning. Pelin Ayranci*, Phung Lai*, NhatHai Phan, Han Hu, David Newman, Alexander Kalinowski, and Dejing Dou. Journal of Combinatorial Optimization - Springer. (*: Co-first author)

• FLSys: Toward an Open Ecosystem for Federated Learning Mobile Apps. Xiaopeng Jiang*, Han Hu*, Thinh On, Phung Lai, Vijaya Datta Mayyuri, An Chen, Devu M. Shila, Adriaan Larmuseau, Ruoming Jin, Cristian Borcea, and NhatHai Phan. IEEE Transactions on Mobile Computing (IEEE TMC). (*: Co-first author)

• Heterogeneous Randomized Response for Differential Privacy in Graph Neural Networks. Khang Tran, Phung Lai, NhatHai Phan, Issa Khalil, Yao Ma, Abdallah Khreishah, My Thai, and Xintao Wu. IEEE BigData 2022. [Oral Presentation]

2021

• Continual Learning with Differential Privacy. Pradnya Desai*, Phung Lai*, NhatHai Phan, and My T. Thai. The 28th International Conference on Neural Information Processing (ICONIP'21), December 8 - 12, 2021. [Oral Presentation] [Github] (*: Co-first author) (Pradnya Desai is an honor undergraduate student, under my supervision)

2020

• A novel Attribute-based Symmetric Multiple Instance Learning for  Histopathological Image Analysis. Trung Vu*, Phung Lai*, Raviv Raich, Anh Pham, Xiaoli Z Fern, UK Arvind Rao. IEEE Transactions on Medical Imaging (IEEE T-MI), October 2020. (*: Co-first author)

• Ontology-based Interpretable Machine Learning for Textual Data. Phung Lai, NhatHai Phan, Han Hu, Anuja Badeti, David Newman, and Dejing Dou. The International Joint Conference on Neural Networks (IJCNN'20), July 19 - 24th, 2020, Glasgow (UK). [Github] [Oral Presentation]

2019

• Ontology-based Interpretable Machine Learning with Learnable Anchors. Phung Lai, NhatHai Phan, David Newman, Han Hu, Anuja Badeti, and Dejing Dou. Knowledge Representation & Reasoning Meets Machine Learning (KR2ML) Workshop at NeurIPS'19, December 8-14, 2019, Vancouver, Canada. [Oral Presentation] [pdf]

2018

• ConvMD: Convolutive matrix decomposition for classification of matrix data. Phung Lai, Raviv Raich, and Molly Megraw. IEEE Statistical Signal Processing (SSP) Workshop, June 10-13, 2018, Freiburg im Breisgau, Germany. [Oral Presentation] [pdf]

2016

• Jeffreys prior regularization for logistic regression. Tam Nguyen, Raviv Raich, Phung Lai. IEEE Statistical Signal Processing (SSP) Workshop, June 10-13, 2018, Freiburg im Breisgau, Germany. [Oral Presentation] [pdf]