Data-free generative model stealing – an experimental study
Model stealing attack refers to duplicating the functionalities of a deep learning model, which results in social or economic effect to model owner or leads to further attacks. Generative Artificial Intelligence is becoming more and more popular and influential, but compared to classification models...
Saved in:
Main Author: | Mao, Ruoyi |
---|---|
Other Authors: | Lin Zhiping |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/176957 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Isoflurane and coronary steal
by: Teo, A., et al.
Published: (2012) -
Stable adaptive work-stealing for concurrent many-core runtime systems
by: Cao, Yangjie, et al.
Published: (2013) -
Stealing deep reinforcement learning models for fun and profit
by: CHEN, Kangjie, et al.
Published: (2021) -
The tricky business of copying, stealing and protecting
by: Knowledge@SMU
Published: (2009) -
Parallel processing of streaming media on heterogeneous hosts using work stealing
by: LI QINGRUI
Published: (2010)