Research

Research Areas

My group works across three connected areas, from hardware up to learning algorithms.

HW & AI-HW Security

Side-channel and fault attacks on hardware, and lightweight architecture-level defenses.

Representative work

RAID’25 ShuffleV: A Microarchitectural Defense Strategy against Electromagnetic Side-Channel Attacks in Microprocessors
Oakland’24 Side-Channel-Assisted Reverse-Engineering of Encrypted DNN Hardware Accelerator IP and Attack Surface Exploration
Oakland’24 DeepShuffle: A Lightweight Defense Framework against Adversarial Fault Injection Attacks on Deep Neural Networks in Multi-Tenant Cloud-FPGA

All related papers

ICCAD’26, HOST’26, RAID’25, Oakland’24a, Oakland’24b, DAC’23a, ICCAD’22, FCCM’22, USENIX Security’21, DAC’21a, DAC’21b, ICCAD’20, CHES’20, ICCAD’19

AI Security & Privacy

Attacks on and protections for ML models, covering model IP, content provenance, and private inference.

Representative work

NDSS’25 Probe-Me-Not: Protecting Pre-trained Encoders from Malicious Probing
NeurIPS’24 Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
ICLR’24 ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
MICRO’23 AQ2PNN: Enabling Two-party Privacy-Preserving Deep Neural Network Inference with Adaptive Quantization

All related papers

ECCV’26a, ECCV’26b, TMLR’26, NDSS’25, NeurIPS’24a, ICCAD’24, ICLR’24, DAC’24, NeurIPS’23, MICRO’23, ICCV’23a ICCV’23b, ICCAD’23, ICML’23, ICML’23, DAC’23b, DAC’22a

Efficient & Quantum ML

Algorithm–hardware co-design for learning on resource-constrained platforms and quantum systems.

Representative work

NeurIPS’26 Decompose the Distillation: Interpretable Single-Pass Guidance for Diffusion Models
DAC’25 Towards Training Robustness Against Dynamic Errors in Quantum Machine Learning
NeurIPS’24 GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
ASPLOS’24 MicroVSA: An Ultra-Lightweight Vector Symbolic Architecture-based Classifier Library for Tiny Microcontrollers

All related papers

NeurIPS’26, FCCM’26, ICML’25a, ICML’25b, DAC’25a, DAC’25b, CPAL’25, NeurIPS’24b, ASPLOS’24, tinyML’24, tinyML’23, DAC’22b, tinyML’22

Research Artifacts

See the Research Artifacts page or browse the full list on GitHub.

Research Support

We gratefully acknowledge generous research support from NSF, ONR, ARL, MathWorks, AMD-XILINX, CISCO, the Northeast Microelectronics Coalition, and Northeastern University.

The findings, views, and opinions in our research do not necessarily reflect the official policies of these organizations.

See (some) publicly accessible projects: