Please use this identifier to cite or link to this item:
https://hdl.handle.net/10356/136558
Title: | Investigating robustness of deep learning against adversarial examples | Authors: | Chua, Shan Jing | Keywords: | Engineering Engineering::Computer science and engineering |
Issue Date: | 2019 | Publisher: | Nanyang Technological University | Abstract: | Deep learning has achieved many unprecedented performances in various fields, such as the field of Computer Vision. Deep neural networks have shown many impressive results in solving complex problems, yet, they are still vulnerable to adversarial attacks, which come in the form of subtle, often imperceptible perturbations. These perturbations that are added to the inputs can cause models to predict incorrectly. In this report, we present the effects of adversarial perturbations that are restricted to their low frequency subspace using the MNIST and CIFAR-10 dataset. We also experimented on generating a universal perturbation that is restricted to its low frequency subspace. The generated image-agnostic perturbation was also tested with a common adversarial defense method – JPEG compression, to observe the effectiveness of such defenses against the perturbation. | URI: | https://hdl.handle.net/10356/136558 | Schools: | School of Computer Science and Engineering | Fulltext Permission: | restricted | Fulltext Availability: | With Fulltext |
Appears in Collections: | SCSE Student Reports (FYP/IA/PA/PI) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
INVESTIGATING ROBUSTNESS OF DEEP LEARNING AGAINST ADVERSARIAL EXAMPLES.pdf Restricted Access | 915.43 kB | Adobe PDF | View/Open |
Page view(s)
286
Updated on Mar 28, 2024
Download(s) 50
61
Updated on Mar 28, 2024
Google ScholarTM
Check
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.