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 2305.18558cs.LOcs.LG
收藏

DelBugV:Delta调试神经网络验证器

DelBugV: Delta-Debugging Neural Network Verifiers

The Hebrew University of Jerusalem(耶路撒冷希伯来大学)

Raya Elsaleh, Guy Katz

AI总结:

DelBugV利用自动delta调试技术,将触发DNN验证器错误行为的验证实例大幅简化(最高达99%),从而显著降低调试 faulty 验证器的难度,并在VNN-COMP'21的4个验证引擎上验证了其有效性。

摘要:

深度神经网络(DNNs)正在成为各类系统中关键组成部分。然而,尽管它们取得了成功,却常常出现严重错误;这引发了人们对对其进行形式化验证的浓厚兴趣。不幸的是,DNN验证器是复杂的工具,本身也容易受到健全性缺陷的影响。由于DNN验证器的复杂性以及被验证的DNN的规模,调试此类错误是一项艰巨的任务。在此,我们提出了一种名为DelBugV的新工具,该工具在DNN验证器上使用自动化的delta调试技术。给定一个有故障的DNN验证器和一个正确的验证器作为参照点(或者在某些情况下,仅有一个有故障的验证器),DelBugV能够生成更简单的DNN验证实例,这些实例仍然会触发不良行为——从而极大地促进了对有故障验证器的调试任务。我们的工具是模块化且可扩展的,可以轻松地通过额外的网络简化方法和策略进行增强。为了评估目的,我们在4个DNN验证引擎上运行了DelBugV,这些引擎在2021年神经网络验证竞赛(VNN-COMP'21)中被观察到产生了错误结果。我们能够将许多触发这些故障行为的验证查询简化多达99%。我们认为我们的工作是朝着生产可靠且值得信赖的基于DNN的软件这一最终目标迈出的一步。

英文摘要:

Deep neural networks (DNNs) are becoming a key component in diverse systems across the board. However, despite their success, they often err miserably; and this has triggered significant interest in formally verifying them. Unfortunately, DNN verifiers are intricate tools, and are themselves susceptible to soundness bugs. Due to the complexity of DNN verifiers, as well as the sizes of the DNNs being verified, debugging such errors is a daunting task. Here, we present a novel tool, named DelBugV, that uses automated delta debugging techniques on DNN verifiers. Given a malfunctioning DNN verifier and a correct verifier as a point of reference (or, in some cases, just a single, malfunctioning verifier), DelBugV can produce much simpler DNN verification instances that still trigger undesired behavior -- greatly facilitating the task of debugging the faulty verifier. Our tool is modular and extensible, and can easily be enhanced with additional network simplification methods and strategies. For evaluation purposes, we ran DelBugV on 4 DNN verification engines, which were observed to produce incorrect results at the 2021 neural network verification competition (VNN-COMP'21). We were able to simplify many of the verification queries that trigger these faulty behaviors, by as much as 99%. We regard our work as a step towards the ultimate goal of producing reliable and trustworthy DNN-based software.

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。

↑