cs.AI updates on arXiv.org 8小时前
BadViM: Backdoor Attack against Vision Mamba
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文提出针对Vision Mamba架构的后门攻击框架BadViM,揭示其易受攻击的弱点,并通过实验证明BadViM的有效性和对防御措施的抵抗力。

arXiv:2507.00577v1 Announce Type: cross Abstract: Vision State Space Models (SSMs), particularly architectures like Vision Mamba (ViM), have emerged as promising alternatives to Vision Transformers (ViTs). However, the security implications of this novel architecture, especially their vulnerability to backdoor attacks, remain critically underexplored. Backdoor attacks aim to embed hidden triggers into victim models, causing the model to misclassify inputs containing these triggers while maintaining normal behavior on clean inputs. This paper investigates the susceptibility of ViM to backdoor attacks by introducing BadViM, a novel backdoor attack framework specifically designed for Vision Mamba. The proposed BadViM leverages a Resonant Frequency Trigger (RFT) that exploits the frequency sensitivity patterns of the victim model to create stealthy, distributed triggers. To maximize attack efficacy, we propose a Hidden State Alignment loss that strategically manipulates the internal representations of model by aligning the hidden states of backdoor images with those of target classes. Extensive experimental results demonstrate that BadViM achieves superior attack success rates while maintaining clean data accuracy. Meanwhile, BadViM exhibits remarkable resilience against common defensive measures, including PatchDrop, PatchShuffle and JPEG compression, which typically neutralize normal backdoor attacks.

Fish AI Reader

Fish AI Reader

AI辅助创作,多种专业模板,深度分析,高质量内容生成。从观点提取到深度思考,FishAI为您提供全方位的创作支持。新版本引入自定义参数,让您的创作更加个性化和精准。

FishAI

FishAI

鱼阅,AI 时代的下一个智能信息助手,助你摆脱信息焦虑

联系邮箱 441953276@qq.com

相关标签

ViM架构 后门攻击 BadViM 安全漏洞 防御措施
相关文章