arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.19936cs.LGcs.AI
收藏

泛化与成员推断攻击:实际视角

Generalization and Membership Inference Attack a Practical Perspective

Department of Computer Engineering Sharif University of Technology Tehran, Iran(计算机工程系 巴尔赫大学 波斯湾伊朗)

Fateme Rahmani, Mahdi Jafari Siavoshani, Mohammad Hossein Rohban

AI总结:

本文通过实证方法探讨MIA成功率与模型泛化之间的关系,发现先进泛化技术可显著降低攻击性能,同时提升模型泛化并减少攻击效果。

摘要:

随着新评估指标和攻击方法的出现,重新评估先前接受的假设变得至关重要。本文回顾了长期存在的关于MIA成功率与模型泛化之间相关性的争论,通过实证方法重新审视。我们专注于使用增强技术和早停法来提高模型泛化,并分析其对MIA成功率的影响。我们发现,使用先进泛化技术可显著降低攻击性能,可能减少多达100倍。此外,结合这些方法不仅提高模型泛化,还通过训练期间引入随机性减少攻击效果。此外,我们的研究通过在受控环境中分析超过1000个模型,确认了泛化对MIA性能的直接影响。

英文摘要:

With the emergence of new evaluation metrics and attack methodologies for Membership Inference Attacks (MIA), it becomes essential to reevaluate previously accepted assumptions. In this paper, we revisit the longstanding debate regarding the correlation between MIA success rates and model generalization using an empirical approach. We focused on employing augmentation techniques and early stopping to enhance model generalization and examined their impact on MIA success rates. We found that utilizing advanced generalization techniques can significantly decrease attack performance, potentially by up to 100 times. Moreover, combining these methods not only improves model generalization but also reduces attack effectiveness by introducing randomness during training. Additionally, our study confirmed the direct impact of generalization on MIA performance through an analysis of over 1K models in a controlled environment.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑