SHF: Medium: More Reliable Image Networks through Scene-based Specification, Neuro-symbolic Training, and Systematic Specification-driven Testing

SHF：中：通过基于场景的规范、神经符号训练和系统规范驱动测试实现更可靠的图像网络

• 批准号: 2312487
• 负责人: Sebastian Elbaum
• 金额: $ 117.47万
• 依托单位: University of Virginia Main Campus
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-07-01 至 2027-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2312487&HistoricalAwards=false
• 关键词: SHF; Medium; More; Reliable; Image

Deep Neural Networks (DNN) are becoming an essential part of safety-critical autonomous systems, from automobiles to medical devices. Failures in such safety-critical autonomous systems may lead to injury or loss of life. Although there are mature techniques for improving the accuracy of DNNs, such techniques do not provide guarantees that the behavior of a DNN will always be appropriate. Without such guarantees the deployment of DNNs in safety and mission critical systems will be limited or unnecessarily risky. This project seeks to assure the quality of image-based DNNs through the development of techniques that change two fundamental current practices: 1) the specification of desirable DNN properties will be abstracted from the pixel-level to domain entities (e.g., people, cars) to enable reasoning about the correctness of DNN behaviors, and 2) the application of those properties will pervade the DNN development process so that the resulting DNNs behave in accordance with those properties. If successful, the research will improve assurance of systems that include DNNs and, thereby, the safety of the public. Modern image Deep Neural Networks can be extremely complex accepting high-resolution images and processing them through many dozens of layers with tens of millions of parameters to compute outputs. Methods of assessing and improving the statistical accuracy of computed outputs relative to labeled training data are in regular use, but such methods provide no guarantees that the behavior of the DNN will be appropriate, especially on unusual or rare inputs. This project seeks to establish the foundations, algorithms and engineering advances for a new approach to developing image-based DNNs with behavior guarantees. The project shifts the direction from prior research that has focused on reasoning about limited forms of DNN correctness at the pixel level, such as local robustness, and instead aims to enable the specification of higher-level properties that abstract from pixel-level variation to describe equivalence classes of behavior and then to incorporate such specifications through the training, testing, and deployment of DNNs. The project activities include developing: 1) a high-level symbolic method for specifying necessary correctness properties of pixel-based DNNs; 2) methods to incorporate such specifications into the training of DNNs so as to guarantee their specification conformance; and 3) methods to assess and improve training, test, and validation sets to ensure that they adequately represent important, but rare, inputs and thereby enable DNNs to generalize to such inputs. Collectively, this work will establish the first high-level approach to specifying the intended behavior of image DNNs and, if successful, the project will provide a foundation for building more reliable DNN-enabled systems.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

深度神经网络（DNN）正在成为从汽车到医疗设备等安全关键型自主系统的重要组成部分。这种安全关键的自主系统中的故障可能导致伤害或生命损失。虽然有成熟的技术来提高DNN的准确性，但这些技术并不能保证DNN的行为总是适当的。 如果没有这样的保证，DNN在安全和使命关键系统中的部署将受到限制或具有不必要的风险。该项目旨在通过开发改变两个基本当前实践的技术来确保基于图像的DNN的质量：1）所需DNN属性的规范将从像素级抽象到域实体（例如，人、汽车），以实现关于DNN行为的正确性的推理，以及2）这些属性的应用将遍及DNN开发过程，使得所得到的DNN根据这些属性来表现。 如果成功，该研究将提高包括DNN在内的系统的保证，从而提高公众的安全性。现代图像深度神经网络可以非常复杂地接受高分辨率图像，并通过具有数千万个参数的数十个层来处理它们以计算输出。 评估和提高计算输出相对于标记训练数据的统计准确性的方法经常使用，但这些方法不能保证DNN的行为是适当的，特别是在不寻常或罕见的输入上。 该项目旨在为开发具有行为保证的基于图像的DNN的新方法建立基础，算法和工程进展。该项目改变了先前研究的方向，该研究专注于在像素级推理DNN正确性的有限形式，例如局部鲁棒性，而是旨在实现从像素级变化中抽象的更高级别属性的规范，以描述行为的等价类，然后通过DNN的训练，测试和部署来纳入这些规范。项目活动包括：1）开发一种高级符号方法，用于指定基于像素的DNN的必要正确性; 2）将这些规范纳入DNN训练的方法，以保证其规范一致性;以及3）评估和改进训练、测试和验证集的方法，以确保它们充分代表重要的，但罕见的，输入，从而使DNN能够泛化到这样的输入。总的来说，这项工作将建立第一个高层次的方法来指定图像DNN的预期行为，如果成功，该项目将为构建更可靠的DNN启用系统奠定基础。该奖项反映了NSF的法定使命，并被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估来支持。