NDLI: Adversarial examples detection through the sensitivity in space mappings

Content Provider	IET Digital Library
Author	Li, Xurong Ji, Shouling Ji, Juntao Ren, Zhenyu Wu, Chunming Li, Bo Wang, Ting
Abstract	Adversarial examples (AEs) against deep neural networks (DNNs) raise wide concerns about the robustness of DNNs. Existing detection mechanisms are often limited to a given attack algorithm. Therefore, it is highly desirable to develop a robust detection approach that remains effective for a large group of attack algorithms. In addition, most of the existing defences only perform well for small images (e.g. MNIST and Canadian institute for advanced research (CIFAR)) rather than large images (e.g. ImageNet). In this paper, the authors propose a robust and effective defence method for analysing the sensitivity of various AEs, especially in a much harder case (large images). Their method first creates a feature map from the input space to the new feature space, by utilising 19 different feature mapping methods. Then, a detector is learned with the machine-learning algorithm to recognise the unique distribution of AEs. Their extensive evaluations on their proposed detector show that their detector can achieve: (i) low false-positive rate (<1%), (ii) high true-positive rate (higher than 98%), (iii) low overhead (<0.1 s per input), and (iv) good robustness (work well across different learning models, attack algorithms, and parameters), which demonstrate the efficacy of the proposed detector in practise.
Starting Page	201
Ending Page	213
Page Count	13
ISSN	17519632
Volume Number	14
e-ISSN	17519640
Issue Number	Issue 5, Aug (2020)
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/iet-cvi/14/5
Alternate Webpage(s)	https://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2019.0378
Journal	IET Computer Vision
Publisher Date	2020-02-25
Access Restriction	Open
Rights Holder	© The Institution of Engineering and Technology
Subject Keyword	Adversarial Examples Detection AE Detection Computer Vision And Image Processing Technique Deep Neural Network Detection Mechanisms DNN Feature Mapping Feature Space Learning in AI Machine Learning Neural Computing Technique Neural Nets Object Detection Optical, Image And Video Signal Processing Space Mappings
Content Type	Text
Resource Type	Article
Subject	Computer Vision and Pattern Recognition Software

Sl.	Authority	Responsibilities	Communication Details
1	Ministry of Education (GoI), Department of Higher Education	Sanctioning Authority	https://www.education.gov.in/ict-initiatives
2	Indian Institute of Technology Kharagpur	Host Institute of the Project: The host institute of the project is responsible for providing infrastructure support and hosting the project	https://www.iitkgp.ac.in
3	National Digital Library of India Office, Indian Institute of Technology Kharagpur	The administrative and infrastructural headquarters of the project	Dr. B. Sutradhar bsutra@ndl.gov.in
4	Project PI / Joint PI	Principal Investigator and Joint Principal Investigators of the project	Dr. B. Sutradhar bsutra@ndl.gov.in Prof. Saswat Chakrabarti will be added soon
5	Website/Portal (Helpdesk)	Queries regarding NDLI and its services	support@ndl.gov.in
6	Contents and Copyright Issues	Queries related to content curation and copyright issues	content@ndl.gov.in
7	National Digital Library of India Club (NDLI Club)	Queries related to NDLI Club formation, support, user awareness program, seminar/symposium, collaboration, social media, promotion, and outreach	clubsupport@ndl.gov.in
8	Digital Preservation Centre (DPC)	Assistance with digitizing and archiving copyright-free printed books	dpc@ndl.gov.in
9	IDR Setup or Support	Queries related to establishment and support of Institutional Digital Repository (IDR) and IDR workshops	idr@ndl.gov.in

YOLOpeds: efficient real-time single-shot pedestrian detection for smart camera applications

Multi-scale deep neural network for salient object detection

Siamese adversarial network for object tracking

A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning

Multi-scale object detection by bottom-up feature pyramid network

Deep learning for multiple object tracking: a survey

Object detection using convolutional networks with adaptively adjusting receptive field of convolutional filter

Accurate and fast single shot multibox detector

Multimodal deep network learning-based image annotation

Adversarial examples detection through the sensitivity in space mappings

Similar Documents

YOLOpeds: efficient real-time single-shot pedestrian detection for smart camera applications

Multi-scale deep neural network for salient object detection

Siamese adversarial network for object tracking

A Novel Simple Visual Tracking Algorithm Based on Hashing and Deep Learning

Multi-scale object detection by bottom-up feature pyramid network

Deep learning for multiple object tracking: a survey

Object detection using convolutional networks with adaptively adjusting receptive field of convolutional filter

Accurate and fast single shot multibox detector

Multimodal deep network learning-based image annotation

Adversarial examples detection through the sensitivity in space mappings