Investigating the Backdoor on DNNs Based on Recolorization and Reconstruction: From a Multi-Channel Perspective-Reference-Cited by-同舟云学术

Investigating the Backdoor on DNNs Based on Recolorization and Reconstruction: From a Multi-Channel Perspective

Published:2024 Issue: Volume:19 Page:6923-6934
ISSN:1556-6013
Container-title:IEEE Transactions on Information Forensics and Security
language:
Short-container-title:IEEE Trans.Inform.Forensic Secur.

Author:

Chen Honglong¹^ORCID,Gao Yudong¹^ORCID,Zhang Anqing¹^ORCID,Sun Peng²^ORCID,Jiang Nan³^ORCID,Liu Weifeng¹^ORCID,Wang Xingang⁴

Affiliation:

1. College of Control Science and Engineering, China University of Petroleum (East China), Qingdao, China

2. College of Computer Science and Electronic Engineering, Hunan University, Changsha, China

3. College of Information Engineering, East China Jiaotong University, Nanchang, China

4. Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China

Funder

Shandong Provincial Taishan Scholar Program, China

Shandong Provincial Natural Science Foundation, China

National Natural Science Foundation of China

Open Project of Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Qilu University of Technology

Young Elite Scientists Sponsorship Program by China Association for Science and Technology

Natural Science Foundation of Hainan Province

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Link

http://xplorestaging.ieee.org/ielx8/10206/10319981/10596291.pdf?arnumber=10596291

Reference48 articles.

1. Towards Personalized Privacy-Preserving Truth Discovery Over Crowdsourced Data Streams

2. AI-Empowered Speed Extraction via Port-Like Videos for Vehicular Trajectory Analysis

3. Backdoor Attack on Deep Learning-Based Medical Image Encryption and Decryption Network

4. Imperceptible and Robust Backdoor Attack in 3D Point Cloud

5. AttrLeaks on the Edge: Exploiting Information Leakage from Privacy-Preserving Co-inference