Our Research
Advancing robust AI: Federated learning, intrusion detection, and privacy-preserving techniques
Welcome to SPRAI Lab
Delve in to AI security research
Join Us
Find Openings below to join the lab
About
SPRAI Lab focuses on the research of Trustworthy AI Systems
SPRAI Lab is led by Dr. Ning Wang, an assistant professor in the Department of Computer Science and Engineering at the University of South Florida (USF). Our mission is to enhance the security and privacy of AI systems, applying advanced machine learning and deep learning methods to solve pressing problems in cybersecurity.
Dr. Wang's research interests include federated learning, network intrusion detection, adversarial machine learning, differential privacy, and the application of large language models (LLMs) in cybersecurity. Under her guidance, the lab explores innovative approaches to trustworthy and robust AI.
The SPRAI Lab welcomes students and collaborators passionate about advancing these fields and making AI systems safer and more reliable for everyone.
Openings
Selected Papers
BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning
View PaperNoiSec: Harnessing Noise for Security against Adversarial and Backdoor Attacks
View PaperScale-mia: A scalable model inversion attack against secure federated learning via latent space reconstruction
View PaperFlare: defending federated learning against model poisoning attacks via latent space representations
View PaperFeCo: Boosting intrusion detection capability in IoT networks via contrastive learning
View PaperMANDA: On Adversarial Example Detection for Network Intrusion Detection System
View PaperNews from
the Lab
- Mar 2025 Our paper ‘Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks’ has been accepted by ESORICS 2025.
- Feb 2025 Our paper ‘Beyond Uniformity: Robust Backdoor Attacks on Deep Neural Networks with Trigger Selection’ has been accepted by PAKDD.
- Feb 2025 Our paper ‘FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning’ has been accepted by TDSC.
- Jan 2025 Dr. Ning Wang will serve as a chair for MILCOM 2025 Track 3.
- Dec 2024 Our paper ‘FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations’ has been accepted by TDSC.
- Dec 2024 Our paper ‘Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction’ has been accepted by NDSS 2025.
- Aug 2024 Our paper ‘Adversarial Attacks on Federated Learning Revisited: a Client-Selection Perspective’ has been accepted to IEEE CNS 2024.
- Aug 2024 Our paper ‘Hermes: Boosting the Performance of Machine-Learning-based Intrusion Detection System through Geometric Feature Learning’ is accepted by ACM MobiHoc 2024.
- July 2024 Dr. Ning Wang will serve as a TPC member for AsiaCCS.
- May 2024 Dr. Ning Wang will serve as a TPC member for NDSS 2025 (fall cycle), IEEE MILCOM 2025, IEEE INFOCOM 2025 (also as Web Chair), and AACD co-located with ACM CCS 2024.
- Feb. 2024 Dr. Ning Wang will serve as a TPC member for WiseML 2024 in conjunction with ACM WiSec 2024.
- March 2024 [New Member] Sudharshan Balaji joined our group
- January 2024 [New Member] Zhengyuan Jiang Joined our group
- August 2023 [Selected Paper] our paper MINDFL: Mitigating the Impact of Imbalanced and Noisy-Labeled Data in Federated Learning with Quality and Fairness-Aware Client Selection’ is accepted by IEEE Military Communications Conference (MILCOM 2023)
- August 2023 [Start] Dr. Ning Wang joined the CSE department and formed the SPRAI lab