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 2409.01249cs.LGcs.CRcs.CV
收藏

对抗剪枝:面向对抗鲁棒性的剪枝方法综述与基准

Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness

University of Cagliari(卡利亚里大学);Sapienza University of Rome(罗马大学);University of Genova(热那亚大学);CINI, National Cybersecurity Lab, Consorzio Interuniversitario Nazionale per l’Informatica(意大利国家跨大学信息学联盟国家网络安全实验室)

Giorgio Piras, Maura Pintor, Ambra Demontis, Battista Biggio, Giorgio Giacinto, Fabio Roli

AI总结:

本文综述了当前的对抗剪枝方法并提出基于流水线和具体细节的新分类法,同时提出公平评估基准并对现有方法进行经验性重评估,揭示了表现最佳方法的共同特征与常见问题。

摘要:

近期工作提出了神经网络剪枝技术,以在减小网络规模的同时保持对对抗样本(即精心制作的诱导误分类的输入)的鲁棒性。这些我们称之为对抗剪枝方法的方法涉及复杂且明确的设计,使得分析差异并建立公平准确的比较变得困难。在本工作中,我们通过综述当前的对抗剪枝方法并提出一种新的分类法来解决这些问题,该分类法基于两个主要维度对它们进行分类:定义何时剪枝的流水线;以及定义如何剪枝的具体细节。然后,我们强调了当前经验分析的局限性,并提出了一种新颖、公平的评估基准来解决这些问题。最后,我们对当前的对抗剪枝方法进行了经验性重评估并讨论了结果,强调了表现最佳的对抗剪枝方法的共同特征以及常见问题。我们欢迎在公开的基准 https://github.com/pralab/AdversarialPruningBenchmark 中做出贡献。

英文摘要:

Recent work has proposed neural network pruning techniques to reduce the size of a network while preserving robustness against adversarial examples, i.e., well-crafted inputs inducing a misclassification. These methods, which we refer to as adversarial pruning methods, involve complex and articulated designs, making it difficult to analyze the differences and establish a fair and accurate comparison. In this work, we overcome these issues by surveying current adversarial pruning methods and proposing a novel taxonomy to categorize them based on two main dimensions: the pipeline, defining when to prune; and the specifics, defining how to prune. We then highlight the limitations of current empirical analyses and propose a novel, fair evaluation benchmark to address them. We finally conduct an empirical re-evaluation of current adversarial pruning methods and discuss the results, highlighting the shared traits of top-performing adversarial pruning methods, as well as common issues. We welcome contributions in our publicly-available benchmark at https://github.com/pralab/AdversarialPruningBenchmark

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。

↑