Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/165393
Title: NASPY: automated extraction of automated machine learning models
Authors: Lou, Xiaoxuan
Guo, Shangwei
Li, Jiwei
Wu, Yaoxin
Zhang, Tianwei
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2022
Source: Lou, X., Guo, S., Li, J., Wu, Y. & Zhang, T. (2022). NASPY: automated extraction of automated machine learning models. The Tenth International Conference on Learning Representations (ICLR 2022).
Project: NRF2018NCR-NCR009-0001 
MOE-T1-RS02/19 
NTU-SUG 
Conference: The Tenth International Conference on Learning Representations (ICLR 2022)
Abstract: We present NASPY, an end-to-end adversarial framework to extract the networkarchitecture of deep learning models from Neural Architecture Search (NAS). Existing works about model extraction attacks mainly focus on conventional DNN models with very simple operations, or require heavy manual analysis with lots of domain knowledge. In contrast, NASPY introduces seq2seq models to automatically identify novel and complicated operations (e.g., separable convolution,dilated convolution) from hardware side-channel sequences. We design two models (RNN-CTC and transformer), which can achieve only 3.2% and 11.3% error rates for operation prediction. We further present methods to recover the model hyper-parameters and topology from the operation sequence . With these techniques, NASPY is able to extract the complete NAS model architecture with high fidelity and automation, which are rarely analyzed before.
URI: https://hdl.handle.net/10356/165393
URL: https://openreview.net/group?id=ICLR.cc/2022/Conference#spotlight-submissions
Schools: School of Computer Science and Engineering 
Rights: © 2022 The Author(s). All rights reserved. This paper was published in Proceedings of The Tenth International Conference on Learning Representations (ICLR 2022) and is made available with permission of The Author(s).
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Conference Papers

Files in This Item:
File Description SizeFormat 
_ICLR2022_NASPY_DRNTU.pdf823.55 kBAdobe PDFThumbnail
View/Open

Page view(s)

149
Updated on Jun 14, 2024

Download(s) 50

82
Updated on Jun 14, 2024

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.