薄冰上的样本：重新评估神经网络的对抗性剪枝
Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks
AI总结：
本研究重新评估三种对抗性剪枝方法，发现其鲁棒性被高估，并揭示靠近决策边界的样本在剪枝后易被误分类，为未来设计更有效的对抗性剪枝方法提供方向。
摘要：
神经网络剪枝已被证明是一种有效的网络压缩技术，通过牺牲泛化性和对抗攻击鲁棒性等理想属性来换取更高的稀疏性。近期研究声称，对抗性剪枝方法能够在生成稀疏网络的同时保持对对抗样本的鲁棒性。在本工作中，我们首先重新评估了三种最先进的对抗性剪枝方法，表明其鲁棒性确实被高估了。随后，我们比较了同一模型的剪枝版本与稠密版本，发现处于“薄冰”状态的样本，即更接近未剪枝模型决策边界的样本，在剪枝后通常会被错误分类。最后，我们讨论了这一直觉如何可能为未来设计更有效的对抗性剪枝方法提供指导。
英文摘要：
Neural network pruning has shown to be an effective technique for reducing the network size, trading desirable properties like generalization and robustness to adversarial attacks for higher sparsity. Recent work has claimed that adversarial pruning methods can produce sparse networks while also preserving robustness to adversarial examples. In this work, we first re-evaluate three state-of-the-art adversarial pruning methods, showing that their robustness was indeed overestimated. We then compare pruned and dense versions of the same models, discovering that samples on thin ice, i.e., closer to the unpruned model's decision boundary, are typically misclassified after pruning. We conclude by discussing how this intuition may lead to designing more effective adversarial pruning methods in future work.
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。
