Invisible trigger image: A dynamic neural backdoor attack based on hidden feature
Authors:
- Xiong ChenXCXiong Chen
- Mohan LiMLMohan Li
- Yanbin SunYSYanbin Sun
- Zhihong TianZTZhihong Tian
- 25 April 2025
- journal article
- Published by Elsevier in Neurocomputing
- Vol. 639
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62272119)
- National Natural Science Foundation of China (U2468204)
- National Natural Science Foundation of China (62372129)
- National Natural Science Foundation of China (62372126)
- National Natural Science Foundation of China (U2436208)
- Chinese Academy of Engineering (2023-JB-13)
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515030142)
- Basic and Applied Basic Research Foundation of Guangdong Province (2025A04J2947)
- Key Laboratory of Trustworthy Distributed Computing and Service of Ministry of Education
- Beijing University of Posts and Telecommunications
This publication has 13 references indexed in Scilit:
- An Embarrassingly Simple Backdoor Attack on Self-supervised Learning2023
- Backdoor Cleansing with Unlabeled Data2023
- Few-shot Backdoor Defense Using Shapley Estimation2022
- BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning2022
- Invisible Backdoor Attack with Sample-Specific Triggers2021
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Image quality assessment: from error visibility to structural similarityIEEE Transactions on Image Processing, 2004