cs.AI updates on arXiv.org 32分钟前
Breaking the Illusion of Security via Interpretation: Interpretable Vision Transformer Systems under Attack
index_new5.html
../../../zaker_core/zaker_tpl_static/wap/tpl_guoji1.html

 

本文研究了结合解释模型的ViT模型在对抗攻击下的脆弱性,提出了一种名为AdViT的攻击方法,在白盒和黑盒场景下均取得100%攻击成功率。

arXiv:2507.14248v1 Announce Type: cross Abstract: Vision transformer (ViT) models, when coupled with interpretation models, are regarded as secure and challenging to deceive, making them well-suited for security-critical domains such as medical applications, autonomous vehicles, drones, and robotics. However, successful attacks on these systems can lead to severe consequences. Recent research on threats targeting ViT models primarily focuses on generating the smallest adversarial perturbations that can deceive the models with high confidence, without considering their impact on model interpretations. Nevertheless, the use of interpretation models can effectively assist in detecting adversarial examples. This study investigates the vulnerability of transformer models to adversarial attacks, even when combined with interpretation models. We propose an attack called "AdViT" that generates adversarial examples capable of misleading both a given transformer model and its coupled interpretation model. Through extensive experiments on various transformer models and two transformer-based interpreters, we demonstrate that AdViT achieves a 100% attack success rate in both white-box and black-box scenarios. In white-box scenarios, it reaches up to 98% misclassification confidence, while in black-box scenarios, it reaches up to 76% misclassification confidence. Remarkably, AdViT consistently generates accurate interpretations in both scenarios, making the adversarial examples more difficult to detect.

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

ViT模型 对抗攻击 解释模型 AdViT 攻击成功率
相关文章