西安电子科技大学学报（自然科学版）2026，Vol.53Issue(3)：135-150,16.DOI:10.19665/j.issn1001-2400.20260104
FID筛选和噪声优化的清洁标签后门攻击方法
Clean-label backdoor attack method with FID-guided screening and noise optimization
摘要
Abstract
To address the limitations of existing Clean-Label Backdoor Attack(CLBA)methods,namely,the lack of consideration for sample distribution discrepancies in the feature space and the insufficient weaken-ing of robustness features through conventional noise,this paper proposes a clean-label backdoor attack method with Frechet Inception Distance(FID)-guided sample selection and noise optimization.First,a Sample Selection Method Based on Feature Discrepancy and Recognizability Constraint(FDRC-SSM)is employed to compute the mean feature vector for each class in the dataset.For each sample,the FID between its feature vector and the class mean is calculated.Samples with large FID values and classification losses below a predefined threshold are selected as training candidates.Next,a Noise Optimization Method Driven by Feature Displacement(FDD-NOM)is used to add perturbations to the selected samples.Under the constraint of preserving correct label predictions,the noise intensity is iteratively adjusted to guide the sample feature distribution in the direction of continuously increasing differences,thereby obtaining optimized noise.Finally,optimized noise and a predefined trigger are injected into the selected samples to generate poisoned data,which are used to train the backdoored model.Experimental results demonstrate that,compared with existing approaches,the proposed method achieves a 1.71%to 14.11%improvement in the attack success rate(ASR)while maintaining a nearly unchanged classification accuracy on benign samples,indicating its effectiveness in clean-label backdoor attacks.关键词
后门攻击/特征提取/样本筛选/噪声优化Key words
backdoor attack/feature extraction/sample selection/noise optimization分类
信息技术与安全科学引用本文复制引用
谢丽霞,康鹏程,杨宏宇,胡俊成..FID筛选和噪声优化的清洁标签后门攻击方法[J].西安电子科技大学学报（自然科学版）,2026,53(3):135-150,16.基金项目
国家自然科学基金民航联合研究基金重点项目(U2433205) （U2433205）
