.png){kind=icon}
返回
Attribution guided purification against adversarial patch
.png){kind=icon}
PRE
AI
DOI：10.1016/j.displa.2024.102720.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Adversarial patch is a threat to computer vision systems, as they can mislead the deep learning model by adding carefully designed stickers or patterns into images. This vulnerability has posed a serious challenge to the application of DNNs in security -critical domains such as security vision systems and autonomous driving. Researchers are actively working on defense strategies to counter adversarial patches. In this paper, a plug -andplay solution defense method is proposed that combines traditional masking with purification techniques. We implement the defense by leveraging a credible attribution algorithm mechanism. Compared to other heuristic methods, our approach minimizes the destruction of input images, reduces the distribution shift introduced by masking, and offers attack -agnostic protection without a carefully designed deep learning model. Our evaluation shows that our approach successfully enhances the security of computer vision systems against adversarial patches, safeguarding their trustworthiness in various applications.
Keyword:
Deep learning
Adversarial defense
Adversarial patch
Diffusion model
期刊
IF:
3.4
论文数:
2.2K
被引数:
3.2K
机构
引用论文
.png){kind=icon}
The power of obfuscation techniques in malicious JavaScript code: A measurement study恶意JavaScript代码中混淆技术的功能: 一项测量研究
OAAI
OAAI分享收藏Oxidative stress in liver of grass carp Ctenopharyngodon idella naturally infected with Saprolegnia parasitica and its influence on disease pathogenesis天然感染水蚤的草鱼肝脏氧化应激及其对疾病发病机制的影响
PREAI
分享收藏Effects of Cooling Rate on Impact Toughness of an Ultrahigh-Strength TRIP-Aided Martensitic Steel
PREAI
分享收藏 没有更多内容
没有更多内容