.png){kind=icon}
返回
IBD: An Interpretable Backdoor-Detection Method via Multivariate Interactions
.png){kind=icon}
OA
AI
DOI：10.3390/s22228697.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent work has shown that deep neural networks are vulnerable to backdoor attacks. In comparison with the success of backdoor-attack methods, existing backdoor-defense methods face a lack of theoretical foundations and interpretable solutions. Most defense methods are based on experience with the characteristics of previous attacks, but fail to defend against new attacks. In this paper, we propose IBD, an interpretable backdoor-detection method via multivariate interactions. Using information theory techniques, IBD reveals how the backdoor works from the perspective of multivariate interactions of features. Based on the interpretable theorem, IBD enables defenders to detect backdoor models and poisoned examples without introducing additional information about the specific attack method. Experiments on widely used datasets and models show that IBD achieves a 78% increase in average in detection accuracy and an order-of-magnitude reduction in time cost compared with existing backdoor-detection methods.
Keyword:
deep neural network
backdoor detection
interpretable deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksBadNets: 评估对深度神经网络的后台攻击.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏分享收藏分享收藏
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
查看更多内容