Zhifeng Lin

Zhifeng Lin

Auto-generated profile, based on publicly available information

Zhifeng Lin

School of Mathematics and Statistics, Fuzhou University, Fuzhou, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2021
Verified
Conference Paper
Closed access
KNKrishna Giri Narra
Krishna Giri Narra
ZLZhifeng Lin
Zhifeng Lin
YWYongqin Wang
Yongqin Wang
KBKeshav Balasubramanian
Keshav Balasubramanian
MAMurali Annavaram
Murali Annavaram
This work presents Origami, a framework which provides privacy-preserving inference for large deep neural network (DNN) models through a combination of enclave execution, cryptographic blinding, interspersed with accelerator-based computation. Origami partitions the ML model into multiple partitions. The first partition receives the encrypted user input within an SGX enclave. The enclave decrypts the input and then applies cryptographic blinding to the input data and the model parameters. The layer computation is offloaded to a GPU/CPU and the computed output is returned to the enclave, which decodes the computation on noisy data using the unblinding factors privately stored within SGX. This process may be repeated for each DNN layer, as has been done in prior work Slalom. However, the overhead of blinding and unblinding the data is a limiting factor to scalability. Origami relies on the empirical observation that the feature maps after the first several layers can not be used, even by a powerful conditional GAN adversary to reconstruct input. Hence, Origami dynamically switches to executing the rest of the DNN layers directly on an accelerator. We empirically demonstrate that using Origami, a conditional GAN adversary, even with an unlimited inference budget, cannot reconstruct the input. Compared to running the entire VGG-19 model within SGX, Origami inference improves the performance of private inference from 11x while using Slalom to 15. 1x.

23 August 2022 in Scientific Programming
Verified
Journal Article
Open access
PDF file
ZLZhifeng Lin
Zhifeng Lin
ZGZhenghua Gu
Zhenghua Gu
ZHZhipeng Huang
Zhipeng Huang
XBXiqiong Bai
Xiqiong Bai
LLLixuan Luo
Lixuan Luo
GLGeng Lin
Geng Lin
The complexity of physical verification increases rapidly with fast shrinking technology nodes. Considering only design rule checking (DRC) constraints or lithography models cannot capture the side physical effects in the fabrication process well. Thus, it is desirable to consider a more general physical verification problem with various types of hotspots. In this paper, we apply machine learning which is based on pixel-based feature extraction to deal with the generalized hotspot detection problem. First, a two-dimensional discrete Fourier transformation-based pixel extraction method is proposed to alleviate the shifting effect and produce stable hotspot features. Then, a pattern-based layout scanning approach is developed to enhance the program efficiency while preserving good detection accuracy. Finally, we design two false alarm reduction strategies to effectively reduce the number of detected nonhotspots and further improve the accuracy of hotspot position. Experimental results based on the industrial benchmarks show that our algorithm outperforms three competitive works in terms of accuracy, false alarm rate, efficiency, and time.

27 October 2024
Verified
Conference Paper
Open access
XTXingyu Tong
Xingyu Tong
GCGuohao Chen
Guohao Chen
MWMin Wei
Min Wei
ZCZhijie Cai
Zhijie Cai
PZPeng Zou
Peng Zou
JCJianli Chen
Jianli Chen