Please use this identifier to cite or link to this item:
Title: Trustworthiness and certified robustness for deep learning
Authors: Xia, Song
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Xia, S. (2022). Trustworthiness and certified robustness for deep learning. Master's thesis, Nanyang Technological University, Singapore.
Project: ICP1900093
Abstract: Though Deep Learning (DL) has shown its superiority in many complex computer vision tasks, in recent years, researchers found out that DL-based systems were extremely vulnerable to adversarial attacks. By adding small and human imperceptible corruptions to the original inputs, adversarial attacks will generate adversarial examples, which, though being very similar to original inputs, could mislead DL with a highly successful rate. Randomized smoothing (RS) is a recently proposed method to provide the certified robustness for DL, which could guarantee any adversarial attack ineffective within a certain range. By using Gaussian estimation, Randomized Smoothing (RS) gives the worst-case decision boundary of DL towards all possible adversarial attacks. Under the worst-case situation, RS gives a certified robustness radius, within which, DL system is guaranteed to return a constant prediction, meaning that no adversarial attack can be effective. Currently, there are two problems in RS. First is that the optimization of directly maximizing certified robustness radius is non-differentiable, due to hard 0-1 mapping and Monte Carlo sampling. The second is that the useful information from original data is corrupted, due to high variance level Gaussian noise. To solve above problems, this dissertation first analyzes current robustness estimation optimization methods and proposes a new generalized consistency optimization, which consists of a looser accuracy item and a tighter robustness item. Meanwhile, this dissertation utilizes linear decomposition to decompose the data according to the value of co-variance and select the useful information. Experiment results show that our proposed generalized consistency optimization with linear decomposition outperforms previous methods and achieves new state-of-the-art results.
Schools: School of Electrical and Electronic Engineering 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:MSE Theses

Files in This Item:
File Description SizeFormat 
Trustworthiness And Certified Robustness For Deep Learning.pdf
  Restricted Access
3.01 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 6, 2023


Updated on Jun 6, 2023

Google ScholarTM


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