CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Binyan, Yang, Fan, Dai, Xilin, Tang, Di, Zhang, Kehuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918104107319296
author Xu, Binyan
Yang, Fan
Dai, Xilin
Tang, Di
Zhang, Kehuan
author_facet Xu, Binyan
Yang, Fan
Dai, Xilin
Tang, Di
Zhang, Kehuan
contents Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low effectiveness against advanced attacks like clean-label and clean-image backdoors. To address them, we introduce CLIP-Guided backdoor Defense (CGD), an efficient and effective method that mitigates various backdoor attacks. CGD utilizes a publicly accessible CLIP model to identify inputs that are likely to be clean or poisoned. It then retrains the model with these inputs, using CLIP's logits as a guidance to effectively neutralize the backdoor. Experiments on 4 datasets and 11 attack types demonstrate that CGD reduces attack success rates (ASRs) to below 1% while maintaining clean accuracy (CA) with a maximum drop of only 0.3%, outperforming existing defenses. Additionally, we show that clean-data-based defenses can be adapted to poisoned data using CGD. Also, CGD exhibits strong robustness, maintaining low ASRs even when employing a weaker CLIP model or when CLIP itself is compromised by a backdoor. These findings underscore CGD's exceptional efficiency, effectiveness, and applicability for real-world backdoor defense scenarios. Code: https://github.com/binyxu/CGD.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05113
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
Xu, Binyan
Yang, Fan
Dai, Xilin
Tang, Di
Zhang, Kehuan
Multimedia
Cryptography and Security
Machine Learning
68T07
I.2.6
Deep Neural Networks (DNNs) are susceptible to backdoor attacks, where adversaries poison training data to implant backdoor into the victim model. Current backdoor defenses on poisoned data often suffer from high computational costs or low effectiveness against advanced attacks like clean-label and clean-image backdoors. To address them, we introduce CLIP-Guided backdoor Defense (CGD), an efficient and effective method that mitigates various backdoor attacks. CGD utilizes a publicly accessible CLIP model to identify inputs that are likely to be clean or poisoned. It then retrains the model with these inputs, using CLIP's logits as a guidance to effectively neutralize the backdoor. Experiments on 4 datasets and 11 attack types demonstrate that CGD reduces attack success rates (ASRs) to below 1% while maintaining clean accuracy (CA) with a maximum drop of only 0.3%, outperforming existing defenses. Additionally, we show that clean-data-based defenses can be adapted to poisoned data using CGD. Also, CGD exhibits strong robustness, maintaining low ASRs even when employing a weaker CLIP model or when CLIP itself is compromised by a backdoor. These findings underscore CGD's exceptional efficiency, effectiveness, and applicability for real-world backdoor defense scenarios. Code: https://github.com/binyxu/CGD.
title CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
topic Multimedia
Cryptography and Security
Machine Learning
68T07
I.2.6
url https://arxiv.org/abs/2507.05113