梳理对抗鲁棒性剪枝方法，提出新分类与公平评估基准
Adversarial Pruning: A Survey and Benchmark of Pruning Methods for Adversarial Robustness
- 按剪枝时机与方式构建双维度分类体系
- 发现顶尖方法共性并揭示当前评估缺陷
- 开源基准支持后续研究对比与改进
近期工作提出了在保持对抗鲁棒性前提下压缩神经网络规模的剪枝技术，这类方法称为对抗剪枝。由于设计复杂、流程多样，现有方法难以系统比较。本文通过全面调研现有对抗剪枝方法，提出基于两个核心维度的新分类体系：剪枝流程（何时剪枝）和剪枝细节（如何剪枝）。同时，指出现有实证分析的局限性，并构建新的公平评估基准以解决这些问题。通过对现有方法的重新评估，揭示了表现优异方法的共同特征及普遍存在的问题。项目已开源，欢迎参与：https://github.com/pralab/AdversarialPruningBenchmark
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。