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 2007.00772cs.LGcs.CRstat.ML
收藏

基于程序规范化的鲁棒准确的作者归属

Robust and Accurate Authorship Attribution via Program Normalization

Visa Research(维萨研究院);University of Wisconsin-Madison(威斯康星大学麦迪逊分校)

Yizhen Wang, Mohannad Alhanahnah, Ke Wang, Mihai Christodorescu, Somesh Jha

摘要:

由于深度学习的快速发展,源代码归因方法已经实现了惊人的准确性。然而,最近的研究揭示了他们对对抗攻击的脆弱性。特别是,他们很容易被试图伪造另一作者或掩盖原作者的对手所欺骗。为了解决这些新出现的问题,我们制定了一个通用的威胁模型,$\textit{relational adversary}$,允许任意数量的语义保持转换应用到任何问题空间的输入,这个安全挑战。我们的理论研究表明,鲁棒性的条件和鲁棒性和精度之间的权衡深度。出于这些见解,我们提出了一种新的学习框架,$\textit{normalize-and-predict}$($\textit{N&P}$),在理论上保证了任何作者归属方法的鲁棒性。我们进行了广泛的评估$\textit{N&P}$在捍卫两个最新的作者归属的方法对国家的最先进的攻击方法。我们的评估表明,$\textit{N&P}$将对抗性输入的准确性提高了70%。更重要的是,$\textit{N&P}$还将鲁棒准确率提高到比对抗训练高45%,同时运行速度快40倍以上。

英文摘要:

Source code attribution approaches have achieved remarkable accuracy thanks to the rapid advances in deep learning. However, recent studies shed light on their vulnerability to adversarial attacks. In particular, they can be easily deceived by adversaries who attempt to either create a forgery of another author or to mask the original author. To address these emerging issues, we formulate this security challenge into a general threat model, the $\textit{relational adversary}$, that allows an arbitrary number of the semantics-preserving transformations to be applied to an input in any problem space. Our theoretical investigation shows the conditions for robustness and the trade-off between robustness and accuracy in depth. Motivated by these insights, we present a novel learning framework, $\textit{normalize-and-predict}$ ($\textit{N&P}$), that in theory guarantees the robustness of any authorship-attribution approach. We conduct an extensive evaluation of $\textit{N&P}$ in defending two of the latest authorship-attribution approaches against state-of-the-art attack methods. Our evaluation demonstrates that $\textit{N&P}$ improves the accuracy on adversarial inputs by as much as 70% over the vanilla models. More importantly, $\textit{N&P}$ also increases robust accuracy to 45% higher than adversarial training while running over 40 times faster.

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。

↑