Collaborative Research: FMitF: Track II: Enhancing the Neural Network Verification (NNV) Tool for Industrial Applications

合作研究:FMitF:轨道 II:增强工业应用的神经网络验证 (NNV) 工具

基本信息

  • 批准号:
    2220426
  • 负责人:
  • 金额:
    $ 4.93万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-10-01 至 2025-03-31
  • 项目状态:
    未结题

项目摘要

The safety and reliability of systems incorporating machine-learning components are significant challenges. New techniques are crucial to enable rigorous analysis before deploying these data-driven machine-learning components for tasks ranging from sensing and perception to planning and control in safety-critical domains, such as aerospace and automotive systems. This project enhances the Neural Network Verification (NNV) software tool for deep neural networks and learning-enabled autonomous systems to enable industrial usage through engagement with industry partners in aerospace, automotive, and design automation. The project's novelty is the development of new verification techniques for neural networks that process time-series data and new ways to specify temporal behaviors. The project's impact is developing and applying rigorous analysis methods, as well as helping transition these methods to industry, which may eventually be used in the engineering-assurance and certification processes of real-world learning-enabled systems.This project will develop new neural-network verification methods for time-series data and architectures, then implement these in the NNV software tool, and evaluate them on challenging benchmarks and case studies from industry. The new time-series analysis techniques combine the relaxed star reachability approach with counterexample-guided abstraction refinement (CEGAR) methods to improve verification scalability while maintaining precision. Trace-based properties for these time-series problems will be specified in formalisms such as metric temporal logic (MTL) and signal temporal logic (STL), as well as extensions of these logics. NNV will also be improved for usability and documentation, as well as evaluated for these improvements, in part by continuing to use it within courses taught by the researchers, as well as collaborating with industry partners. Industrial-scale benchmarks and case studies developed with industry partners will strengthen engagement of the broader formal-methods and machine-learning research communities through events such as the Neural Network Verification Competition (VNN-COMP) and the Hybrid Systems Verification (ARCH-COMP) category on Artificial Intelligence and Neural Network Control Systems (AINNCS).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.
包含机器学习组件的系统的安全性和可靠性是一个重大挑战。在部署这些数据驱动的机器学习组件之前,新技术至关重要,以便在航空航天和汽车系统等安全关键领域部署从传感和感知到规划和控制的各种任务之前进行严格的分析。该项目增强了神经网络验证(NNV)软件工具,用于深度神经网络和支持学习的自主系统,通过与航空航天、汽车和设计自动化领域的行业合作伙伴进行合作,实现工业应用。该项目的新奇之处在于开发了用于处理时间序列数据的神经网络的新验证技术,以及指定时间行为的新方法。该项目的影响是开发和应用严格的分析方法,并帮助将这些方法转化为行业,最终可能用于真实世界学习系统的工程保证和认证过程。该项目将为时间序列数据和体系结构开发新的神经网络验证方法,然后在NNV软件工具中实施这些方法,并在行业的挑战性基准和案例研究中对它们进行评估。新的时间序列分析技术结合了松弛的星可达性方法和反例引导的抽象求精(CEGAR)方法,在保持精度的同时提高了验证的可扩展性。这些时间序列问题的基于迹的性质将在诸如度量时态逻辑(MTL)和信号时态逻辑(STL)以及这些逻辑的扩展的形式化中被指定。NNV还将在可用性和文档方面进行改进,并对这些改进进行评估,部分原因是通过在研究人员教授的课程中继续使用NNV,以及与行业合作伙伴合作。与行业合作伙伴共同开发的工业规模基准和案例研究将通过神经网络验证竞赛(VNN-COMP)和人工智能和神经网络控制系统(AINNCS)混合系统验证(ARCH-COMP)类别等活动,加强更广泛的形式方法和机器学习研究社区的参与。该奖项反映了NSF的法定使命,并通过使用基金会的智力优势和更广泛的影响审查标准进行评估,被认为值得支持。

项目成果

期刊论文数量(4)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Robustness Verification of Deep Neural Networks using Star-Based Reachability Analysis with Variable-Length Time Series Input
  • DOI:
    10.48550/arxiv.2307.13907
  • 发表时间:
    2023-07
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Neelanjana Pal;Diego Manzanas Lopez;Taylor T. Johnson
  • 通讯作者:
    Neelanjana Pal;Diego Manzanas Lopez;Taylor T. Johnson
Benchmark: Formal Verification of Semantic Segmentation Neural Networks
基准:语义分割神经网络的形式化验证
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Neelanjana Pal;Seojin Lee;Taylor T. Johnson
  • 通讯作者:
    Taylor T. Johnson
First three years of the international verification of neural networks competition (VNN-COMP)
  • DOI:
    10.1007/s10009-023-00703-4
  • 发表时间:
    2023-01
  • 期刊:
  • 影响因子:
    1.5
  • 作者:
    Christopher Brix;Mark Niklas Muller;Stanley Bak;Taylor T. Johnson;Changliu Liu
  • 通讯作者:
    Christopher Brix;Mark Niklas Muller;Stanley Bak;Taylor T. Johnson;Changliu Liu
NNV 2.0: The Neural Network Verification Tool
NNV 2.0:神经网络验证工具
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Diego Manzanas Lopez;Sung Woo Choi;Hoang-Dung Tran;Taylor T. Johnson
  • 通讯作者:
    Taylor T. Johnson
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Taylor Johnson其他文献

QRIS: A Quantitative Reflectance Imaging System for the Pristine Sample of Asteroid Bennu
QRIS:小行星贝努原始样本的定量反射成像系统
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Ruby E. Fulford;D. Golish;D. Lauretta;D. DellaGiustina;Steve Meyer;Nicole Lunning;Christopher Snead;K. Righter;J. Dworkin;Carina A. Bennett;H. C. Connolly;Taylor Johnson;A. Polit;Pierre Haennecour;Andrew J. Ryan
  • 通讯作者:
    Andrew J. Ryan
Phytochemical Nrf2 activator attenuates skeletal muscle mitochondrial dysfunction and impaired proteostasis in a preclinical model of musculoskeletal aging
植物化学 Nrf2 激活剂可减轻肌肉骨骼衰老临床前模型中骨骼肌线粒体功能障碍和蛋白质稳态受损
  • DOI:
    10.1101/2021.06.11.448143
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0
  • 作者:
    R. Musci;K. Andrie;M. Walsh;Z. Valenti;Maryam F. Afzali;Taylor Johnson;Thomas E. Kail;Richard B Martinez;Tessa Nguyen;Joseph L. Sanford;Meredith D. Murrell;J. McCord;B. Hybertson;B. Miller;Qian Zhang;M. Javors;K. Santangelo;K. Hamilton
  • 通讯作者:
    K. Hamilton
Trends in Female Authorship in Orthopaedic Literature from 2002 to 2021
2002年至2021年骨科文献女性作者趋势
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yasmine S. Ghattas;Cynthia Kyin;A. Grise;Jillian Glasser;Taylor Johnson;Katherine Druskovich;Lisa K. Cannada;Benjamin C. Service
  • 通讯作者:
    Benjamin C. Service
Quantifying hazards resilience by modeling infrastructure recovery as a resource constrained project scheduling problem
通过将基础设施恢复建模为资源受限的项目调度问题来量化灾害恢复力
  • DOI:
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Taylor Johnson;J. Leandro;D. Ahadzie
  • 通讯作者:
    D. Ahadzie
Racial Disparities Effect On Hospital Length Of Stay In Patients With Left Ventricular Assist Device-related Complications
种族差异对左心室辅助装置相关并发症患者住院时间的影响
  • DOI:
    10.1016/j.cardfail.2024.10.059
  • 发表时间:
    2025-01-01
  • 期刊:
  • 影响因子:
    8.200
  • 作者:
    Mariel Duchow;Kristina Menchaca;Gordon White;Taylor Johnson;Juzer Ali Asgar;Claire Lucero;Catherine Ostos;Waqas Ghumman
  • 通讯作者:
    Waqas Ghumman

Taylor Johnson的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Taylor Johnson', 18)}}的其他基金

NSF Workshop on Safety and Trust in Artificial Intelligence Enabled Systems
NSF 人工智能支持系统安全与信任研讨会
  • 批准号:
    2231543
  • 财政年份:
    2022
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
FMitF: Track I: Generative Neural Network Verification in Medical Imaging Analysis
FMITF:第一轨:医学影像分析中的生成神经网络验证
  • 批准号:
    2220401
  • 财政年份:
    2022
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: Operator theoretic methods for identification and verification of dynamical systems
合作研究:动力系统识别和验证的算子理论方法
  • 批准号:
    2028001
  • 财政年份:
    2020
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
SHF: Small: Collaborative Research: Fuzzing Cyber-Physical System Development Tool Chains with Deep Learning (DeepFuzz-CPS)
SHF:小型:协作研究:利用深度学习模糊网络物理系统开发工具链 (DeepFuzz-CPS)
  • 批准号:
    1910017
  • 财政年份:
    2019
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
FMitF: Track II: Hybrid and Dynamical Systems Verification on the CPS-VO
FMITF:轨道 II:CPS-VO 上的混合动力系统验证
  • 批准号:
    1918450
  • 财政年份:
    2019
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
SHF: Small: Automating Improvement of Development Environments for Cyber-Physical Systems (AIDE-CPS)
SHF:小型:自动改进网络物理系统的开发环境 (AIDE-CPS)
  • 批准号:
    1736323
  • 财政年份:
    2016
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
CRII: CPS: Safe Cyber-Physical Systems Upgrades
CRII:CPS:安全网络物理系统升级
  • 批准号:
    1713253
  • 财政年份:
    2016
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
CRII: CPS: Safe Cyber-Physical Systems Upgrades
CRII:CPS:安全网络物理系统升级
  • 批准号:
    1464311
  • 财政年份:
    2015
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
SHF: Small: Automating Improvement of Development Environments for Cyber-Physical Systems (AIDE-CPS)
SHF:小型:自动改进网络物理系统的开发环境 (AIDE-CPS)
  • 批准号:
    1527398
  • 财政年份:
    2015
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant

相似国自然基金

Research on Quantum Field Theory without a Lagrangian Description
  • 批准号:
    24ZR1403900
  • 批准年份:
    2024
  • 资助金额:
    0.0 万元
  • 项目类别:
    省市级项目
Cell Research
  • 批准号:
    31224802
  • 批准年份:
    2012
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research
  • 批准号:
    31024804
  • 批准年份:
    2010
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Cell Research (细胞研究)
  • 批准号:
    30824808
  • 批准年份:
    2008
  • 资助金额:
    24.0 万元
  • 项目类别:
    专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
  • 批准号:
    10774081
  • 批准年份:
    2007
  • 资助金额:
    45.0 万元
  • 项目类别:
    面上项目

相似海外基金

FMitF: Collaborative Research: RedLeaf: Verified Operating Systems in Rust
FMITF:协作研究:RedLeaf:经过验证的 Rust 操作系统
  • 批准号:
    2313411
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Game Theoretic Updates for Network and Cloud Functions
合作研究:FMitF:第一轨:网络和云功能的博弈论更新
  • 批准号:
    2318970
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Knitting Semantics
合作研究:FMitF:第一轨:针织语义
  • 批准号:
    2319182
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Towards Verified Robustness and Safety in Power System-Informed Neural Networks
合作研究:FMitF:第一轨:实现电力系统通知神经网络的鲁棒性和安全性验证
  • 批准号:
    2319242
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: DeepSmith: Scheduling with Quality Guarantees for Efficient DNN Model Execution
合作研究:FMitF:第一轨:DeepSmith:为高效 DNN 模型执行提供质量保证的调度
  • 批准号:
    2349461
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Towards Verified Robustness and Safety in Power System-Informed Neural Networks
合作研究:FMitF:第一轨:实现电力系统通知神经网络的鲁棒性和安全性验证
  • 批准号:
    2319243
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Synthesis and Verification of In-Memory Computing Systems using Formal Methods
合作研究:FMitF:第一轨:使用形式方法合成和验证内存计算系统
  • 批准号:
    2319400
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Synthesis and Verification of In-Memory Computing Systems using Formal Methods
合作研究:FMitF:第一轨:使用形式方法合成和验证内存计算系统
  • 批准号:
    2319399
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: Simplifying End-to-End Verification of High-Performance Distributed Systems
合作研究:FMitF:第一轨:简化高性能分布式系统的端到端验证
  • 批准号:
    2318954
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
Collaborative Research: FMitF: Track I: The Phlox framework for verifying a high-performance distributed database
合作研究:FMitF:第一轨:用于验证高性能分布式数据库的 Phlox 框架
  • 批准号:
    2319167
  • 财政年份:
    2023
  • 资助金额:
    $ 4.93万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了