Academic Journal
method for machine learning backdoor attacks based on defense method based on diffusion models
| Title: | method for machine learning backdoor attacks based on defense method based on diffusion models |
|---|---|
| Authors: | WANG Sunping, ZHANG Aiqing, YE Xinrong, WANG Yong |
| Source: | 网络与信息安全学报, Vol 11, Pp 137-148 (2025) |
| Publisher Information: | POSTS&TELECOM PRESS Co., LTD, 2025. |
| Publication Year: | 2025 |
| Collection: | LCC:Electronic computers. Computer science |
| Subject Terms: | machine learning, backdoor attack, trigger, diffusion model, Electronic computers. Computer science, QA75.5-76.95 |
| Description: | Backdoor attacks were recognized as one of the primary security threats faced by machine learning models during the training phase. Although significant progress had been achieved in existing defense methods against backdoor attacks, these approaches were often found to result in a substantial decline in model accuracy on clean test sets. To address this issue, a method named defending against backdoor attacks with diffusion model (DBADM) was proposed. The core idea of this method was to preprocess poisoned samples containing backdoor triggers using a diffusion model before model training. By altering the hidden trigger features in the samples, backdoor attacks were effectively mitigated. Systematic offensive and defensive comparison experiments were conducted on four benchmark datasets: MNIST, CIFAR-10, Tiny ImageNet, and LFW. The experimental results demonstrate that the DBADM method not only successfully defends against various backdoor attacks but also maintains the model’s high accuracy performance on the clean dataset. |
| Document Type: | article |
| File Description: | electronic resource |
| Language: | English Chinese |
| ISSN: | 2096-109X |
| Relation: | http://www.cjnis.com.cn/thesisDetails#10.11959/j.issn.2096-109x.2025059; https://doaj.org/toc/2096-109X |
| DOI: | 10.11959/j.issn.2096-109x.2025059 |
| Access URL: | https://doaj.org/article/652580024f434cb3bee22b51cc60144a |
| Accession Number: | edsdoj.652580024f434cb3bee22b51cc60144a |
| Database: | Directory of Open Access Journals |
| ISSN: | 2096109X |
|---|---|
| DOI: | 10.11959/j.issn.2096-109x.2025059 |