一句话：提出面向深度神经网络的自动验证与测试技术，对有界输入扰动给出可达输出集的上下界，并提供可证明保证。
随着计算系统日益复杂、决策越来越多地依赖深度学习组件，自动驾驶、医学诊断等安全攸关应用对可靠性提出了严峻要求；而深度网络对对抗扰动的不稳定性使传统软件开发方法难以直接适用。本报告介绍针对深度神经网络的自动化验证与测试技术的进展，旨在保证网络决策在输入有界扰动下的安全性与鲁棒性。其核心思路是利用网络的 Lipschitz 连续性，对给定输入集合近似计算出网络可达输出集的上下界，并以 anytime（任意时间可中断、逐步精化）方式给出可证明的保证。作者发展了基于特征引导搜索、博弈、全局优化与贝叶斯方法的新算法，并在当前最先进的网络上进行了评估。报告最后概述了该领域尚存的挑战。
Computing systems are becoming ever more complex, with decisions increasingly often based on deep learning components. A wide variety of applications are being developed, many of them safety-critical, such as self-driving cars and medical diagnosis. Since deep learning is unstable with respect to adversarial perturbations, there is a need for rigorous software development methodologies that encompass machine learning components. This lecture will describe progress with developing automated verification and testing techniques for deep neural networks to ensure safety and robustness of their decisions with respect to bounded input perturbations. The techniques exploit Lipschitz continuity of the networks and aim to approximate, for a given set of inputs, the reachable set of network outputs in terms of lower and upper bounds, in anytime manner, with provable guarantees. We develop novel algorithms based on feature-guided search, games, global optimisation and Bayesian methods, and evaluate them on state-of-the-art networks. The lecture will conclude with an overview of the challenges in this field.
DOI 原文 ·
@inproceedings{paperbot5936,
title = {Safety and robustness for deep learning with provable guarantees},
author = {Marta Kwiatkowska},
booktitle = {ASE},
year = {2020},
doi = {10.1145/3324884.3418901}
}