arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.03043cs.LGstat.ML
收藏

Source Code模型的语义鲁棒性

Semantic Robustness of Models of Source Code

University of Wisconsin–Madison(威斯康星大学麦迪逊分校)

Goutham Ramakrishnan, Jordan Henkel, Zi Wang, Aws Albarghouthi, Somesh Jha, Thomas Reps

摘要:

深度神经网络容易受到对抗性样本的影响--小的输入扰动会导致不正确的预测。我们研究这个问题的模型的源代码,我们希望网络是强大的源代码修改,保留代码功能。(1)我们定义了一个强大的对手,可以使用参数序列,语义保持程序转换;(2)我们展示了如何执行对抗训练来学习对这些对手鲁棒的模型;(3)我们对不同的语言和架构进行了评估,证明了鲁棒性的显著量化收益。

英文摘要:

Deep neural networks are vulnerable to adversarial examples - small input perturbations that result in incorrect predictions. We study this problem for models of source code, where we want the network to be robust to source-code modifications that preserve code functionality. (1) We define a powerful adversary that can employ sequences of parametric, semantics-preserving program transformations; (2) we show how to perform adversarial training to learn models robust to such adversaries; (3) we conduct an evaluation on different languages and architectures, demonstrating significant quantitative gains in robustness.

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。

↑