用抽象解释法验证神经网络安全性，确保关键应用中的可靠运行。
Neural Network Verification with PyRAT
- 基于抽象解释构建可达状态分析框架
- 在VNN-Comp 2024中获第二名，验证效率与精度兼备
- 适合需安全保证的医疗、交通等高风险领域
随着人工智能系统在医疗、交通、能源等关键领域广泛应用，确保其安全性和可靠性变得至关重要。为此，本文提出PyRAT，一个基于抽象解释的神经网络验证工具，用于验证神经网络的安全性与鲁棒性。PyRAT通过多种抽象方法，从输入出发追踪神经网络的可达状态，并具备快速准确分析的能力。该工具已在多个合作项目中用于保障系统安全，其在VNN-Comp 2024中取得第二名的成绩，充分体现了其实用性能。
原文摘要 · Abstract (English)
As AI systems are becoming more and more popular and used in various critical domains (health, transport, energy, ...), the need to provide guarantees and trust of their safety is undeniable. To this end, we present PyRAT, a tool based on abstract interpretation to verify the safety and the robustness of neural networks. In this paper, we describe the different abstractions used by PyRAT to find the reachable states of a neural network starting from its input as well as the main features of the tool to provide fast and accurate analysis of neural networks. PyRAT has already been used in several collaborations to ensure safety guarantees, with its second place at the VNN-Comp 2024 showcasing its performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。