Sotabase

Career

· Postdoctoral Researcher, UC Berkeley EECS department and Berkeley AI Research2024–
· Assistant Professor in Electrical and Computer Engineering, University of Arizona2024–

Publications (46)

DPATCH: An Adversarial Patch Attack on Object Detectors
SafeAI@AAAI · 2018
337
cited
Soteria: Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective
Computer Vision and Pattern Recognition · 2020
202
cited
DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensembles
Neural Information Processing Systems · 2020
126
cited
DeepHoyer: Learning Sparser Neural Network with Differentiable Scale-Invariant Sparsity Measures
International Conference on Learning Representations · 2019
107
cited
AtomLayer: A Universal ReRAM-Based CNN Accelerator with Atomic Layer Computation
Design Automation Conference · 2018
104
cited
Sticker: A 0.41-62.1 TOPS/W 8Bit Neural Network Processor with Multi-Sparsity Compatible Convolution Arrays and Online Tuning Acceleration for Fully Connected Layers
2018 IEEE Symposium on VLSI Circuits · 2018
88
cited
Learning Low-rank Deep Neural Networks via Singular Vector Orthogonality Regularization and Singular Value Sparsification
2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · 2020
85
cited
Global Vision Transformer Pruning with Hessian-Aware Saliency
Computer Vision and Pattern Recognition · 2021
80
cited
BSQ: Exploring Bit-Level Sparsity for Mixed-Precision Neural Network Quantization
International Conference on Learning Representations · 2021
78
cited
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
Computer Vision and Pattern Recognition · 2022
70
cited
NViT: Vision Transformer Compression and Parameter Redistribution
arXiv.org · 2021
64
cited
Magic-Me: Identity-Specific Video Customized Diffusion
ECCV Workshops · 2024
54
cited
DeepObfuscator: Obfuscating Intermediate Representations with Privacy-Preserving Adversarial Learning on Smartphones
International Conference on Internet-of-Things Design and Implementation · 2019
53
cited
TIPRDC: Task-Independent Privacy-Respecting Data Crowdsourcing Framework for Deep Learning with Anonymized Intermediate Representations
Knowledge Discovery and Data Mining · 2020
53
cited
APOLLO: An Automated Power Modeling Framework for Runtime Power Introspection in High-Volume Commercial Microprocessors
Micro · 2021
50
cited
DeepObfuscator: Adversarial Training Framework for Privacy-Preserving Image Classification
arXiv.org · 2019
45
cited
Stock Price Movement Prediction from Financial News with Deep Learning and Knowledge Graph Embedding
Pacific Rim Knowledge Acquisition Workshop · 2018
44
cited
Anticipating Stock Market of the Renowned Companies: A Knowledge Graph Approach
Complex · 2019
42
cited
Multi-Objective Optimization of ReRAM Crossbars for Robust DNN Inferencing under Stochastic Noise
2021 IEEE/ACM International Conference On Computer Aided Design (ICCAD) · 2021
37
cited
MAT: A Multi-strength Adversarial Training Method to Mitigate Adversarial Attacks
IEEE Computer Society Annual Symposium on VLSI · 2018
29
cited
Sotabase
Huanrui Yang | Researcher Profile | Sotabase | Sotabase