One-to-Multiple Clean-Label Image Camouflage (OmClic) based backdoor attack on deep learning
Authors:
- Guohong WangGWGuohong Wang
- Hua MaHMHua Ma
- Yansong GaoYGYansong Gao
- Alsharif AbuadbbaAAAlsharif Abuadbba
- Zhi ZhangZZZhi Zhang
- Wei KangWKWei Kang
- Said F. Al-SarawiSASaid F. Al-Sarawi
- Gongxuan ZhangGZGongxuan Zhang
- Derek AbbottDADerek Abbott
- 3 February 2024
- journal article
- research article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 288
Abstract
No abstract availableKeywords
Funding Information
- National Natural Science Foundation of China (62172224, 62272232)
This publication has 18 references indexed in Scilit:
- TransCAB: Transferable Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World2023
- Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks2022
- White-box content camouflage attacks against deep learningComputers & Security, 2022
- Backdoor Attacks Against Deep Learning Systems in the Physical World2021
- Design and Evaluation of a Multi-Domain Trojan Detection Method on Deep Neural NetworksIEEE Transactions on Dependable and Secure Computing, 2021
- Densely Connected Convolutional Networks2017
- Deep Residual Learning for Image Recognition2016
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- MODEC: Multimodal Decomposable Models for Human Pose Estimation2013
- A universal image quality indexIEEE Signal Processing Letters, 2002