Research Artifacts
Our group is committed to reproducible research and releases tools, code, and demonstrations from our work whenever possible.
Recent and Representative Projects
FCCM’26 VSALUT: A Lightweight Low-Dimensional VSA Classifier for Efficient Inference on FPGA [Code]
TMLR’26 Defending Against Image Attribution Forgery Through Content-Dependent Cryptographic Watermarks
RAID’25 ShuffleV: A Microarchitectural Defense Strategy against Electromagnetic Side-Channel Attacks in Microprocessors [Code]
ICML’25 Taming Diffusion for Dataset Distillation with High Representativeness [Code]
NeurIPS’24 Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature [Code]
NeurIPS’24 GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction [Code]
ICCAD’24 AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing [Code]
VL/HCC’24 ALLI/O: An Action-based Visual Programming Language for Embedded System Programming [Code]
ICLR’24 ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor [Code]
ASPLOS’24 MicroVSA: An Ultra-Lightweight Vector Symbolic Architecture-based Classifier Library for Tiny Microcontrollers [Code]
Earlier Projects (2023 and before)
NeurIPS’23 LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference [Code]
ICCV’23 VertexSerum: Poisoning Graph Neural Networks for Link Inference [Code]
ICCV’23 AutoReP: Automatic ReLU Replacement for Fast Private Network Inference [Code]
ICML’23 NNSplitter: An Active Defense Solution to DNN Model via Automated Weight Obfuscation [Code]
ICML’23 Orchestrating Encoding and Sparsity for Fast Homomorphically Encrypted NN Inference [Code]
DAC’23 Polynomial Arch. Search Framework for Two-party Computation-based Secure NN Deployment [Code]
ICCAD’22 ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach [Code] [IEEE/ACM William J. McCalla ICCAD Best Paper Nomination]
DAC’22 LeHDC: Learning-Based Hyperdimensional Computing Classifier [Code]
tinyML’22 A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices [Code]
Security’21 An Adversarial Weight Duplication Attack Framework to Crush DNN in Multi-Tenant FPGA [Code]
DAC’21 SGX-FPGA: Trusted Execution Environment for CPU-FPGA Heterogeneous Architecture [Code]