About me
I am an assistant professor in the Bellini College of Artificial Intelligence, Cybersecurity, and Computing (CAICC) at the University of South Florida (USF).
My research interests include federated learning, network intrusion detection, adversarial machine learning, differential privacy, and LLM application in cybersecurity. Detail about our research can be found at our lab webpage SPRAI.
News
-[Apr. 2026] Our paper ‘Learning from Textual Radiology Reports: A Benchmark Dataset for Coronary CT Angiography’ has been accepted by ACL 2026.
-[Mar. 2026] Our paper ‘Noise, Why Can’t You Bend? Detecting Adversarial Perturbations in Wireless Sensing via Structural Fragility’ has been accepted by AsiaCCS.
-[Feb. 2026] Our paper ‘Two Heads Are Better than One: Model-Weight and Latent-Space Analysis for Federated Learning on Non-iid Data against Model Poisoning Attacks’ has been accepted by PAKDD 2026.
-[Oct. 2025] Our paper ‘Buffer is All You Need: Defending Federated Learning Against Backdoor Attacks Under Non-Iids via Buffering’ has been accepted by IEEE TrustCom.
-[Aug. 2025] Nikhil and Sudharshan Joined SPRAI lab.
-[July 2025] Our paper ‘BoBa: Boosting Backdoor Detection through Data Distribution Inference in Federated Learning’ has been accepted by ECAI 2025
-[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] Ning will serve as a TPC member 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] Ning will serve as a TPC member for AsiaCCS.
-[May 2024] Ning will serve as a TPC member for NDSS 2025 (fall cycle).
-[May 2024] Ning will server as a TPC member for and IEEE MILCOM 2025.
-[May 2024] Ning will serve as a TPC member and Web Chair of IEEE INFOCOM 2025.
-[May 2024] Ning will serve as a TPC member for AACD co-located with ACM CCS 2024.
-[Feb. 2024] Ning will serve as a TPC member for WiseML 2024 in conjunction with ACM WiSec 2024.
-[Aug. 2023] 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). pdf
-[June 2023] Ning will serve as a TPC member for ACM Workshop on Moving Target Defense (MTD) 23 co-located with ACM Conference on Computer and Communications (CCS) 23.
-[Sep. 2022] Our paper Squeezing More Utility via Adaptive Clipping on Deferentially Private Gradients in Federated Meta-Learning is accepted by The Annual Computer Security Applications Conference (ACSAC 2022). pdf code
-[Aug. 2022] Our paper Transferability of Adversarial Examples in Machine Learning-based Malware Detection is accepted by the 2022 IEEE Conference on Communications and Network Security (CNS22). pdf
-[Feb. 2022] Our paper FLARE: Defending Federated Learning against Model Poisoning Attacks via Latent Space Representations is accepted by the 17th ACM ASIA Conference on Computer and Communications Security (AsiaCCS 2022). pdf
-[Feb. 2022] Our paper MANDA: On Adversarial Example Detection for Network Intrusion Detection System is accepted by IEEE Transactions on Dependable and Secure Computing (TDSC). pdf code
-[Dec. 2021] Our paper FeCo: Boosting Intrusion Detection Capability in IoT Networks via Contrastive Learning has been accepted by the 2022 IEEE International Conference on Computer Communications (INFOCOM 2022). pdf code
-[Dec. 2020] Our paper MANDA: On Adversarial Example Detection for Network Intrusion Detection System is accepted by the 2021 IEEE International Conference on Computer Communications (INFOCOM 2021). pdf