activity
20182022
most citedModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

49 citations · 107 across the 6 of their papers we have counts for

collaborators

9 papers

cs.SE2022

Automation Slicing and Testing for in-App Deep Learning Models

Hao Wu, Yuhang Gong, Xiaopeng Ke +5

Intelligent Apps (iApps), equipped with in-App deep learning (DL) models, are emerging to offer stable DL inference services. However, App marketplaces have trouble auto testing iA…

cs.LG202219 cited

SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation

Cong Guo, Yuxian Qiu, Jingwen Leng +6

Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the o…

cs.LG202149 cited

ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection

Yuanchun Li, Ziqi Zhang, Bingyan Liu +2

The knowledge of a deep learning model may be transferred to a student model, leading to intellectual property infringement or vulnerability propagation. Detecting such knowledge r…

cs.AR20212 cited

Dual-side Sparse Tensor Core

Yang Wang, Chen Zhang, Zhiqiang Xie +3

Leveraging sparsity in deep neural network (DNN) models is promising for accelerating model inference. Yet existing GPUs can only leverage the sparsity from weights but not activat…

cs.CR20213 cited

DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection

Yuanchun Li, Jiayi Hua, Haoyu Wang +2

Deep learning models are increasingly used in mobile applications as critical components. Unlike the program bytecode whose vulnerabilities and threats have been widely-discussed,…

cs.SE202034 cited

Dynamic Slicing for Deep Neural Networks

Ziqi Zhang, Yuanchun Li, Yao Guo +2

Program slicing has been widely applied in a variety of software engineering tasks. However, existing program slicing techniques only deal with traditional programs that are constr…