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 2403.00935cs.CRcs.LG
收藏

面向安全的迁移学习:挑战与未来方向

Transfer Learning for Security: Challenges and Future Directions

Purdue University(普渡大学);Cisco Research(思科研究院)

Adrian Shuai Li, Arun Iyengar, Ashish Kundu, Elisa Bertino

AI总结:

本文综述迁移学习在安全任务中的应用进展,分析跨领域知识迁移的价值、现有研究空白及未来方向。

摘要:

许多机器学习和数据挖掘算法都依赖于这样一个假设:训练数据与测试数据共享相同的特征空间和分布。然而,这一假设并不总是成立。例如,在某些情况下,我们需要对一个领域中的数据进行分类,但我们只能从另一个不同的领域获得充足的训练数据。后一类数据可能遵循截然不同的分布。在这种情况下,成功地跨领域迁移知识能够显著提升学习性能,并减少对大量数据标注工作的需求。因此,迁移学习(TL)已成为应对这一挑战的一种很有前景的框架,尤其是在与安全相关的任务中。本文旨在综述将 TL 技术用于安全领域的最新进展。文中讨论了在安全领域应用 TL 时现存的研究空白,并探讨了在 TL 辅助的安全解决方案背景下出现的潜在未来研究方向和问题。

英文摘要:

Many machine learning and data mining algorithms rely on the assumption that the training and testing data share the same feature space and distribution. However, this assumption may not always hold. For instance, there are situations where we need to classify data in one domain, but we only have sufficient training data available from a different domain. The latter data may follow a distinct distribution. In such cases, successfully transferring knowledge across domains can significantly improve learning performance and reduce the need for extensive data labeling efforts. Transfer learning (TL) has thus emerged as a promising framework to tackle this challenge, particularly in security-related tasks. This paper aims to review the current advancements in utilizing TL techniques for security. The paper includes a discussion of the existing research gaps in applying TL in the security domain, as well as exploring potential future research directions and issues that arise in the context of TL-assisted security solutions.

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。

↑