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 2502.13593cs.LGcs.CRcs.CV
收藏

迈向鲁棒的非迁移学习:一项调查与基准

Toward Robust Non-Transferable Learning: A Survey and Benchmark

Sydney AI Centre, The University of Sydney(悉尼人工智能中心,悉尼大学)

Ziming Hong, Yongli Xiang, Tongliang Liu

AI总结:

本文首次全面综述了非迁移学习(NTL),并提出了首个统一基准NTLBench以评估NTL的性能与鲁棒性,揭示了现有方法在抵御攻击方面的局限性。

摘要:

在过去的几十年里,研究人员主要致力于提升模型的泛化能力,却很少关注对这种泛化能力的调节。然而,模型对非预期数据(例如有害或未授权数据)的泛化能力可能会被恶意攻击者以难以预见的方式利用,从而可能导致违反模型伦理。非迁移学习(NTL)是一项旨在重塑深度学习模型泛化能力的任务,被提出用于应对这些挑战。尽管该领域已提出大量方法,但仍缺乏对现有进展的全面回顾以及对当前局限性的深入分析。在本文中,我们通过首次提出关于NTL的全面调查,并引入NTLBench(首个在统一框架下评估NTL性能和鲁棒性的基准)来填补这一空白。具体而言,我们首先介绍NTL的任务设置、通用框架和标准,随后对NTL方法进行总结。此外,我们强调了一个经常被忽视的问题,即针对各种可能破坏NTL建立的非迁移机制的攻击的鲁棒性。通过NTLBench进行的实验验证了现有NTL方法在鲁棒性方面的局限性。最后,我们讨论了NTL的实际应用,以及其未来方向和相关挑战。

英文摘要:

Over the past decades, researchers have primarily focused on improving the generalization abilities of models, with limited attention given to regulating such generalization. However, the ability of models to generalize to unintended data (e.g., harmful or unauthorized data) can be exploited by malicious adversaries in unforeseen ways, potentially resulting in violations of model ethics. Non-transferable learning (NTL), a task aimed at reshaping the generalization abilities of deep learning models, was proposed to address these challenges. While numerous methods have been proposed in this field, a comprehensive review of existing progress and a thorough analysis of current limitations remain lacking. In this paper, we bridge this gap by presenting the first comprehensive survey on NTL and introducing NTLBench, the first benchmark to evaluate NTL performance and robustness within a unified framework. Specifically, we first introduce the task settings, general framework, and criteria of NTL, followed by a summary of NTL approaches. Furthermore, we emphasize the often-overlooked issue of robustness against various attacks that can destroy the non-transferable mechanism established by NTL. Experiments conducted via NTLBench verify the limitations of existing NTL methods in robustness. Finally, we discuss the practical applications of NTL, along with its future directions and associated challenges.

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。

↑