.png){kind=icon}
返回
DropBlock: A Structured Regularisation Technique for Mitigating Membership Inference Attacks (MIAs) in Machine Learning Models
.png){kind=icon}
OA
AI
DOI：10.1016/j.icte.2026.01.006.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This study proposes DropBlock, a structured regularization technique, to mitigate Membership Inference Attacks (MIAs). Unlike traditional dropout, DropBlock masks contiguous regions of feature maps during training, disrupting spatial correlations and preventing data memorization. Evaluated on MNIST, CIFAR-10, and CIFAR-100, DropBlock significantly outperforms baseline defenses, reducing MIA success rates by up to 12.8% on CIFAR-10 and 12.1% on CIFAR-100. Furthermore, it suppresses the attack True Positive Rate by over 40% at low false alarm rates while improving classification accuracy by 2–3%. These findings confirm that DropBlock provides a superior and practical defense without requiring noise injection.
Keyword:
Membership Inference Attacks
Privacy-Preserving Machine Learning (PPML)
Privacy
DropBlock
Security
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:
4.2
论文数:
1.0K
被引数:
2.5K
机构
引用论文
.png){kind=icon}
分享收藏Intelligent Event Triggered Lane Keeping Security Control for Autonomous Vehicle Under DoS Attacks智能事件触发式车道保持安全控制：对抗自主车辆中的DoS攻击
PREAI
分享收藏分享收藏Tight incentive analysis of Sybil attacks against the market equilibrium of resource exchange over general networks针对一般网络中资源交换市场均衡的Sybil攻击的紧激励分析
PREAI
分享收藏 没有更多内容
没有更多内容