西安电子科技大学学报（自然科学版）2026，Vol.53Issue(3)：120-134,15.DOI:10.19665/j.issn1001-2400.20260402
基于ViT的高迁移性黑盒对抗样本生成
High-transferability adversarial example generation for the black-box vision transformer
摘要
Abstract
Transfer-based adversarial attacks against convolutional neural networks(CNNs)exploit the observation that models trained on the same task often share similar decision boundaries,crafting examples on a substitute model that transfer to a target.However,due to architectural differences,existing methods struggle to achieve cross-architecture transfer.To address this,we propose the OptiEncode,a Vision Transformer(ViT)‒based method for generating high-transferability black-box adversarial examples.Leverag-ing ViT's strong capability to localize salient features,OptiEncode uses Grad-CAM to identify cross-architecture consensus regions and Sobel to extract architecture-agnostic high-frequency structures,and then injects perturbations only on their intersection to enhance transferability.Unlike SE,PNA,and FPR,which primarily modify the model internals,the OptiEncode explicitly aligns cross-architecture shared features in the input space,thus making it orthogonal and stackable with those approaches.Evaluations on black-box targets across diverse architectures(ViT,CNN,and MLP)show that the OptiEncode improves ViT-to-ViT transfer by about 10%on average and achieves up to 15%gains in cross-architecture settings(e.g.,ViT→CNN).These results indicate that explicitly aligning the"consensus regions ∩ high-frequency structures"in the input space effectively narrows the cross-architecture transfer gap and offers a reusable,complementary path for improving the practicality of black-box transfer attacks.关键词
对抗样本/迁移性/黑盒攻击/深度学习Key words
adversarial example/transferability/black-box attacks/deep learning分类
信息技术与安全科学引用本文复制引用
康行铠,刘洪毅,周慧鹏,王亚杰,祝烈煌..基于ViT的高迁移性黑盒对抗样本生成[J].西安电子科技大学学报（自然科学版）,2026,53(3):120-134,15.基金项目
云南省科技计划项目云南省大数据技术及应用创新中心资助(202605AK340003) （202605AK340003）
云南省重大科技专项计划(202502AD080008) （202502AD080008）
云南省新型研发机构培育对象项目(202404BQ040148) （202404BQ040148）
