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 2108.11651cs.LGcs.PL
收藏

深度神经网络的可扩展模块化鲁棒性分析

Scalable and Modular Robustness Analysis of Deep Neural Networks

National University of Singapore(新加坡国立大学);Guangdong University of Technology(广东工业大学)

Yuyi Zhong, Quang-Trung Ta, Tianzuo Luo, Fanlong Zhang, Siau-Cheng Khoo

摘要:

随着神经网络训练的深入和规模的扩大,对神经网络分析器的可扩展性提出了迫切要求。我们的方法的主要技术见解是模块化地分析神经网络,通过将网络分割成块并对每个块进行分析。特别是,我们提出了网络块摘要技术,以捕捉网络块内的行为使用块摘要和利用摘要,以加快分析过程。我们在最先进的分析器DeepPoly的CPU版本的上下文中实例化我们的方法,并将我们的系统命名为Bounded-Block Poly(BBPoly)。我们在各种实验设置上广泛评估BBPoly。实验结果表明,我们的方法产生了与DeepPoly相当的精度,但运行速度更快,需要更少的计算资源。例如,BBPoly可以分析像SkipNet或ResNet这样的非常大的神经网络,这些网络包含多达100万个神经元,每个输入图像不到1小时,而DeepPoly甚至需要花费40小时来分析一个图像。

英文摘要:

As neural networks are trained to be deeper and larger, the scalability of neural network analyzers is urgently required. The main technical insight of our method is modularly analyzing neural networks by segmenting a network into blocks and conduct the analysis for each block. In particular, we propose the network block summarization technique to capture the behaviors within a network block using a block summary and leverage the summary to speed up the analysis process. We instantiate our method in the context of a CPU-version of the state-of-the-art analyzer DeepPoly and name our system as Bounded-Block Poly (BBPoly). We evaluate BBPoly extensively on various experiment settings. The experimental result indicates that our method yields comparable precision as DeepPoly but runs faster and requires less computational resources. For example, BBPoly can analyze really large neural networks like SkipNet or ResNet which contain up to one million neurons in less than around 1 hour per input image, while DeepPoly needs to spend even 40 hours to analyze one image.

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。

↑