arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.00512cs.LOcs.LG
收藏

基于证明产生式的神经网络验证

Neural Network Verification with Proof Production

The Hebrew University of Jerusalem(希伯来大学);Stanford University(斯坦福大学);East China Normal University(华东师范大学)

Omri Isac, Clark Barrett, Min Zhang, Guy Katz

摘要:

深度神经网络(DNN)越来越多地用于安全关键系统,迫切需要保证其正确性。因此,验证社区已经设计了多种用于验证DNN的技术和工具。当DNN验证器发现触发错误的输入时,很容易确认;但是当他们报告不存在错误时,无法确保验证工具本身没有缺陷。由于在DNN验证工具中已经观察到多个错误,这使得DNN验证的适用性受到质疑。在这项工作中,我们提出了一种新的机制,用于增强基于单纯形的DNN验证器的证明生产能力:生成一个易于检查的不可满足性证据,证明没有错误。我们的证明生产是基于著名的法卡斯引理的有效适应,结合处理分段线性函数和数值精度误差的机制。作为概念证明,我们在Marabou DNN验证器上实现了我们的技术。我们的评估的安全关键系统的空中防撞表明,证明生产成功,在几乎所有的情况下,只需要最小的开销。

英文摘要:

Deep neural networks (DNNs) are increasingly being employed in safety-critical systems, and there is an urgent need to guarantee their correctness. Consequently, the verification community has devised multiple techniques and tools for verifying DNNs. When DNN verifiers discover an input that triggers an error, that is easy to confirm; but when they report that no error exists, there is no way to ensure that the verification tool itself is not flawed. As multiple errors have already been observed in DNN verification tools, this calls the applicability of DNN verification into question. In this work, we present a novel mechanism for enhancing Simplex-based DNN verifiers with proof production capabilities: the generation of an easy-to-check witness of unsatisfiability, which attests to the absence of errors. Our proof production is based on an efficient adaptation of the well-known Farkas' lemma, combined with mechanisms for handling piecewise-linear functions and numerical precision errors. As a proof of concept, we implemented our technique on top of the Marabou DNN verifier. Our evaluation on a safety-critical system for airborne collision avoidance shows that proof production succeeds in almost all cases and requires only minimal overhead.

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。

↑