Publications

My research focuses on trustworthy machine learning, AI security, hardware acceleration for deep learning, and media authentication. Below is a comprehensive list of my publications organized by research area.

Trustworthy Machine Learning

zPROBE: Zero Peek Robustness Checks for Federated Learning

Z. Ghodsi*, M. Javaheripi*, N. Sheyban*, X. Zhang*, K. Huang, & F. Koushanfar
ICCV 2023
Paper | Patent

Abstract

Federated Learning (FL) has emerged as a privacy-preserving paradigm for collaborative model training across distributed clients. However, FL systems remain vulnerable to adversarial attacks that can compromise model performance. This paper introduces zPROBE, a novel framework for zero-peek robustness checks in federated learning environments. Our approach enables secure evaluation of model robustness without requiring access to the underlying data, preserving privacy while ensuring security.

zPROBE: Zero Peek Robustness Checks for Federated Learning

Z. Ghodsi*, M. Javaheripi*, N. Sheybani*, X. Zhang*, K. Huang, & F. Koushanfar
NeurIPS 2022 TSRML Workshop [Outstanding Paper Award]
Paper

Scalable Binary Neural Network Applications in Oblivious Inference

X. Zhang**, M. Samragh, S. Hussain, K. Huang, & F. Koushanfar
**ACM Transactions on Embedded Computing Systems (TECS)
Paper

On the Application of Binary Neural Networks in Oblivious Inference

M. Samragh, S. Hussain, X. Zhang, K. Huang, & F. Koushanfar
CVPR 2021 Workshop
Paper

Media Authentication & Watermarking

FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes

P. Neekhara, S. Hussain, X. Zhang, K. Huang, J. McAuley, F. Koushanfar
ACM Transactions on Multimedia Computing Communications and Applications (TOMM) 2024
Paper | Patent

Abstract

The proliferation of deepfakes and manipulated media poses significant challenges to media authenticity. We present FaceSigns, a semi-fragile neural watermarking technique for media authentication and deepfake detection. Our approach embeds imperceptible watermarks that are robust to benign transformations but fragile to malicious manipulations, enabling effective authentication of genuine media and detection of deepfakes.

FastStamp: Accelerating Neural Steganography and Digital Watermarking of Images on FPGAs

S. Hussain, N. Sheybani, P. Neekhara, X. Zhang, J. Duarte, F. Koushanfar
ICCAD 2022
Paper

Hardware Security

AdaTest: Reinforcement Learning and Adaptive Sampling for On-chip Hardware Trojan Detection

H. Chen, X. Zhang, K. Huang, F. Koushanfar
ACM Transactions on Embedded Computing Systems (TECS) 2022
Paper

SenseHash: Computing on Sensor Values Mystified at the Origin

N. Sheybani, X. Zhang, S. U. Hussain, F. Koushanfar
IEEE Transactions on Emerging Topics in Computing (TETC) 2021
Paper

Real-Time IC Aging Prediction via On-Chip Sensors

K. Huang, M.T.H. Anik, X. Zhang, and N. Karimi
IEEE Computer Society Annual Symposium on VLSI (ISVLSI) 2021
Paper

DEVoT: Dynamic Delay Modeling of Functional Units under Voltage and Temperature Variations

D. Ma, X. Zhang, et al.
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2021
Paper

Real-time Prediction for IC Aging Based on Machine Learning

K. Huang, X. Zhang, and N. Karimi
IEEE Transactions on Instrumentation and Measurement (TIM) 2019
Paper

Patents

1. zPROBE: Zero Peek Robustness Checks for Federated Learning
   Serial No. 63/496,157 (2022)

2. FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes
   Serial No. 63/323,470 (2022)

3. Peasants Joy Precisely Pushes Guiding Device
   CN205754440U (2016)

4. Bicycle Lock Based on Bluetooth
   CN205621091U (2016)

5. Portably Lead Blind Waistband
   CN204766395U (2015)

</div>

Ready to collaborate?

Let's discuss how my expertise in AI security and machine learning can benefit your organization.

Get in Touch Schedule a Call