Welcome to the Secure, Trustworthy, and Reliable AI (Star-AI) Lab.
At Star-AI (★AI) Lab, we focus on cutting-edge research to make the online space safer.
To this end, we develop novel methods in three key areas: AI-enabled cybersecurity, Security of AI, and Privacy of AI. Please see our current projects and publications in each area from our team 😊 .
Recent News
- Our paper, Trustworthy Federated Learning with Local Differential Privacy received the Best Paper Award in WITS 2025 (selected from 156 papers).
- Our paper, Optimal Transport Regularized Divergences: Application to Adversarial Robustness was accepted to SIAM 2025.
- Our paper, RADAR: A Framework for Developing Adversarially Robust Cyber Defense AI Agents with Deep Reinforcement Learning was accepted to MIS Quarterly 2025 (~10% acceptance rate).
- Our paper, Risk-Sensitive Variational Actor-Critic: A Model-Based Approach was accepted to ICLR 2025.
- Our paper, Defending Deep Learning-Based Raw Malware Detectors Against Adversarial Attacks: A Sequence Modeling Approach was accepted to JMIS 2025.
- Our paper, Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security was accepted to TDSC 2025.
- Our paper, Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement was accepted to NeurIPS 2024.
- Our paper, Learning Contextualized Action Representations in Sequential Decision Making for Adversarial Malware Optimization was accepted to TDSC 2024.
- Our paper, Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning was accepted to ACSAC 2024.
- Reza serves as a PC member in IEEE S&P Workshop on Deep Learning Security and Privacy 2023 .
- Reza helps organize IEEE ICDM Workshop on Machine Learning for Cybersecurity (MLC) 2023 .
- Our paper, Heterogeneous Domain Adaptation with Deep Adversarial Representation Learning: Experiments on E-Commerce and Cybersecurity was accepted to IEEE TPAMI 2022.
- Our paper, Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence was accepted to ACM TMIS 2022.
- Our paper, Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach was accepted to IEEE ISI 2021.
- Our paper on Deep Learning-based Privacy Awareness received the Best Paper Award in IEEE ISI 2021.
- Reza serves as Program Committee (PC) Member in IEEE S&P Workshop on Deep Learning and Security (DLS) 2022.
- Our paper, on Binary Black-Box Attacks Against Static Malware Detectors with Reinforcement Learning in Discrete Action Spaces was accepted at IEEE S&P Workshop on Deep Learning and Security (DLS) 2021.
- Our paper, Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model was accepted to the AAAI Conference on Artificial Intelligence, Workshop on Robust, Secure, and Efficient Machine Learning (RSEML), 2021.
- Our Paper on Adversarial Cross-Lingual Knowledge Transfer in Hacker Forums was accepted at IEEE S&P Workshop on Deep Learning and Security (DLS).
Selected Publications
These are some selected publications. Full list of publications and patents.
Â
RADAR: A framework for developing adversarially robust cyber defense AI agents with deep reinforcement learning
MIS Quarterly, 2025
R. Ebrahimi, Y. Chai, W. Li, J. Pacheco, H. Chen
Download
Learning Contextualized Action Representations in Sequential Decision Making for Adversarial Malware Optimization
IEEE TDSC, 2025
R. Ebrahimi, J. Pacheco, J. Hu, H. Chen
Download
Learning Contextualized Action Representations in Sequential Decision Making for Adversarial Malware Optimization
IEEE TDSC, 2025
R. Ebrahimi, J. Pacheco, J. Hu, H. Chen
Download
Defending Deep Learning-based Raw Malware Detectors Against Adversarial Attacks: A Sequence Modeling Approach
JMIS, 2025
R. Ebrahimi, J. Hu, N. Zhang, J. Nunamaker, H.Chen
Download
Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security
IEEE TDSC, 2025
Y. Zhang, R. Behnia, A. Yavuz, R. Ebrahimi, E. Bertino
Download
Optimal Transport Regularized Divergences: Application to Adversarial Robustness
SIAM Journal on Mathematics of Data Science
J. Birrell, R. Ebrahimi
Download
Risk-Sensitive Variational Actor-Critic: A Model-Based Approach
ICLR, 2025
A. Granados, R. Ebrahimi, J. Pacheco
Download
Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
NeurIPS, 2024
J. Birrell, R. Ebrahimi, R. Behnia, J. Pacheco
Download
Efficient Secure Aggregation for Privacy-Preserving Federated Machine Learning
ACSAC, 2024
R. Behnia, A. Riasi, R. Ebrahimi, S. Chow, B. padmanabhan, T. Hoang
Download
Multi-view Representation Learning from Malware to Defend Against Adversarial Variants
IEEE ICDM Workshop on Multi-view Representation Learning, 2022
J. Hu, R. Ebrahimi, W. Li, X. Li, H. Chen
Download
EW-Tune: A Framework for Privately Fine-Tuning Large Language Models with Differential Privacy
IEEE ICDM Workshop on Machine Learning for Cybersecurity, 2022
R. Behnia*, R. Ebrahimi*, J. Pacheco, B. Padmanabhan (* Equal contribution)
Download
Heterogeneous Domain Adaptation with Deep Adversarial Representation Learning: Experiments on E-Commerce and Cybersecurity
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023
R. Ebrahimi, Y. Chai, H. Zhang, H. Chen
Download
Binary Black-Box Attacks Against Static Malware Detectors with Reinforcement Learning in Discrete Action Spaces
IEEE S&P Workshop on Deep Learning and Security (DLS), pp. 85-91, 2021
R. Ebrahimi, J. Pacheco, W. Li, J. Hu, H. Chen
Download
Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model
AAAI Conference on Artificial Intelligence, Workshop on Robust, Secure, and Efficient Machine Learning (RSEML), February 8-9, 2021
R. Ebrahimi, N. Zhang, J. Hu, M. T. Raza, H. Chen
Download
Single-Shot Black-Box Adversarial Attacks Against Malware Detectors: A Causal Language Model Approach
IEEE International Conference on Intelligence and Security Informatics (ISI), 2021
J. Hu, R. Ebrahimi, H. Chen
Download
Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence
ACM TMIS, 2022
N. Zhang, R. Ebrahimi, W. Li, H. Chen
Download
Cross-Lingual Security Analytics: Cyber Threat Detection in the International Dark Web with Adversarial Deep Representation Learning
MIS Quarterly (MISQ), 2022
R. Ebrahimi, Y. Chai, S. Samtani, H. Chen
Download
Founder’s Bio, Curriculum vitae, and Google Scholar
  Reza Ebrahimi
  ebrahimim[ at ]usf.edu
Reza is an assistant professor and the founder of Star-AI Lab at the School of Information Systems and a fellow of the Rapid7 Cyber Threat Intelligence Lab at the University of South Florida (USF). He received his Ph.D. in Management Information Systems from the University of Arizona in 2021. He was a research associate at the Artificial Intelligence (AI) Lab. He received his master’s degree in Computer Science from Concordia University, Canada, in 2016. His Master’s thesis leveraged crime data mining to enhance juveniles’ safety in cyberspace. Reza’s PhD dissertation on AI-enabled cybersecurity analytics won the ACM SIGMIS best doctoral dissertation award in 2021. Reza’s research focuses on statistical and adversarial machine learning for AI-enabled secure and trustworthy cyberspace.
Reza has published over 40 articles in peer reviewed journals, conferences, and workshops, including NeurIPS, ICLR, SIAM, IEEE TPAMI, IEEE TDSC, IEEE S&PW, IEEE ACSAC, AAAIW, IEEE ISI, IEEE ICDMW, Applied Artificial Intelligence, Digital Forensics, MIS Quarterly, and JMIS. He has been serving as a Program Chair and Program Committee member in IEEE ICDM Workshop on Machine Learning for Cybersecurity (MLC) and IEEE S&P Workshop on Deep Learning Security and Privacy (DLSP). He servs as an organizer of 2025 IEEE S&P Workshop on Human-Machine Intelligence for Security Analytics (HMI-SA). He has contributed to several projects supported by the National Science Foundation (NSF). He is an IEEE Senior Member and a member of the ACM, AAAI, and AIS.
