NTD: Non-Transferability Enabled Deep Learning Backdoor Detection-Reference-Cited by-同舟云学术

NTD: Non-Transferability Enabled Deep Learning Backdoor Detection

Published:2024 Issue: Volume:19 Page:104-119
ISSN:1556-6013
Container-title:IEEE Transactions on Information Forensics and Security
language:
Short-container-title:IEEE Trans.Inform.Forensic Secur.

Author:

Li Yinshan¹,Ma Hua²,Zhang Zhi³^ORCID,Gao Yansong⁴^ORCID,Abuadbba Alsharif⁴,Xue Minhui⁴^ORCID,Fu Anmin¹^ORCID,Zheng Yifeng⁵^ORCID,Al-Sarawi Said F.²^ORCID,Abbott Derek²^ORCID

Affiliation:

1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China

2. School of Electrical and Electronics Engineering, The University of Adelaide, Adelaide, SA, Australia

3. Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA, Australia

4. Data61, CSIRO, Canberra, ACT, Australia

5. Harbin Institute of Technology, Shenzhen, China

Funder

National Natural Science Foundation of China

Natural Science Foundation of Jiangsu

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computer Networks and Communications,Safety, Risk, Reliability and Quality

Link

http://xplorestaging.ieee.org/ielx7/10206/10319981/10243095.pdf?arnumber=10243095

Reference65 articles.

1. Trojan Signatures in DNN Weights

2. Deep Learning With Edge Computing: A Review

3. DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks

4. Anti-backdoor learning: Training clean models on poisoned data;li;Proc NIPS,2021

5. Explaining and harnessing adversarial examples;goodfellow;Proc ICLR,2016

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting;2024 IEEE Symposium on Security and Privacy (SP);2024-05-19

2. Sponge Attack Against Multi-Exit Networks With Data Poisoning;IEEE Access;2024

3. On Model Outsourcing Adaptive Attacks to Deep Learning Backdoor Defenses;IEEE Transactions on Information Forensics and Security;2024