CAREER: Enhancing Deep-Learning-based Code Analyses via Human Intelligence

职业:通过人类智能增强基于深度学习的代码分析

基本信息

  • 批准号:
    2146443
  • 负责人:
  • 金额:
    $ 52.71万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2022
  • 资助国家:
    美国
  • 起止时间:
    2022-05-01 至 2027-04-30
  • 项目状态:
    未结题

项目摘要

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).With the increasing availability of the millions of programs in open-source repositories, many techniques have been proposed to leverage deep-learning models to automatically learn patterns from large code bases to assist various software engineering tasks (e.g., security analysis, bug detection). However the proposed deep-learning models still face many input programs that are beyond a model’s handling capability due to many reasons (e.g., evolution of the program code). Because of the lack of understanding about these inputs, many software-engineering applications in industrial practice still make decisions based on symbolic-reasoning systems where decision logic and rules are hard-coded by a human. Human intelligence (e.g., rules summarized by humans) tends to be simplistic and reductionistic, while deep-learning models can be opaque and overfitted. If one can somehow combine the best of the two worlds, many existing challenges will disappear. Therefore, this proposal seeks to make progress on such a combination. The broad goal of this proposal is to design a general framework that improves deep-learning models’ handling of input programs by incorporating human intelligence. Specifically, two main issues are faced by existing deep-learning models in handling code data: (1) lack of understanding about inherent nature of code data, and (2) lack of domain-specific knowledge of software-engineering tasks. To address these fundamental limitations, this project proposes to design a general, user-driven learning-based framework. In the short term, this project aims to improve the practicality of intelligent code-analysis techniques and facilitate the adoption of deep learning techniques in code analysis. In the long run, this project has the potential to fundamentally transform the learning-based techniques for code analysis in software-engineering applications.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.
该奖项全部或部分由《2021年美国救援计划法案》(公法117-2)资助。随着开源存储库中数以百万计的程序的可用性不断增加,人们提出了许多技术来利用深度学习模型从大型代码库中自动学习模式,以协助各种软件工程任务(例如,安全分析,错误检测)。然而,由于许多原因(例如,程序代码的演变),所提出的深度学习模型仍然面临许多超出模型处理能力的输入程序。由于缺乏对这些输入的理解,工业实践中的许多软件工程应用仍然基于符号推理系统做出决策,其中决策逻辑和规则是由人类硬编码的。人类智能(例如,人类总结的规则)往往是简单和简化的,而深度学习模型可能是不透明和过拟合的。如果一个人能以某种方式将这两个世界的优点结合起来,那么许多现有的挑战就会消失。因此,本建议力求在这种结合方面取得进展。该提案的总体目标是设计一个通用框架,通过结合人类智能来改进深度学习模型对输入程序的处理。具体而言,现有深度学习模型在处理代码数据时面临两个主要问题:(1)缺乏对代码数据固有性质的理解;(2)缺乏对软件工程任务的特定领域知识。为了解决这些基本限制,本项目建议设计一个通用的、用户驱动的、基于学习的框架。短期内,该项目旨在提高智能代码分析技术的实用性,并促进深度学习技术在代码分析中的应用。从长远来看,这个项目有潜力从根本上改变软件工程应用程序中基于学习的代码分析技术。该奖项反映了美国国家科学基金会的法定使命,并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,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)
EREBA: Black-box Energy Testing of Adaptive Neural Networks
DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks
NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models
NMTSloth: understanding and testing efficiency degradation of neural machine translation systems
{{ 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 }}

Wei Yang其他文献

Improving Walking Assist Hip Exoskeleton Torque Efficiency with Decoupling Mechanism
利用解耦机构提高步行辅助髋部外骨骼扭矩效率
Artificial Synapses: A Reliable All‐2D Materials Artificial Synapse for High Energy‐Efficient Neuromorphic Computing (Adv. Funct. Mater. 27/2021)
人工突触:用于高能效神经形态计算的可靠全二维材料人工突触(Adv. Funct. Mater. 27/2021)
  • DOI:
    10.1002/adfm.202170197
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    19
  • 作者:
    Jian Tang;Congli He;Jianshi Tang;K. Yue;Qingtian Zhang;Yizhou Liu;Qinqin Wang;Shuopei Wang;Na Li;Cheng Shen;Yanchong Zhao;Jieying Liu;Jiahao Yuan;Zheng Wei;Jiawei Li;Kenji Watanabe;T. Taniguchi;Dashan Shang;Shouguo Wang;Wei Yang;Rong Yang;D. Shi;Guangyu Zhang
  • 通讯作者:
    Guangyu Zhang
Cloning, purification, crystallization and preliminary X-ray studies of HMO2 from Saccharomyces cerevisiae.
酿酒酵母 HMO2 的克隆、纯化、结晶和初步 X 射线研究。
  • DOI:
    10.1107/s2053230x13031580
  • 发表时间:
    2014
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Zhen Guo;Shaocheng;Hongpeng Zhang;Li Jin;Shasha Zhao;Wei Yang;Jian Tang;汪德强
  • 通讯作者:
    汪德强
Vibrational–translational relaxation in nitrogen discharge plasmas: Master equation modeling and Landau–Teller model revisited
氮放电等离子体中的振动平移弛豫:重新审视主方程模型和 Landau Teller 模型
  • DOI:
    10.1063/5.0021993
  • 发表时间:
    2020-10
  • 期刊:
  • 影响因子:
    1.6
  • 作者:
    Wei Yang;Qianhong Zhou;Qiang Sun;Zhiwei Dong;Eryan Yan
  • 通讯作者:
    Eryan Yan
Energy transfer from PSI-generated M1 subharmonic waves to high-frequency internal waves
从 PSI 产生的 M1 次谐波到高频内波的能量转移
  • DOI:
    10.1029/2021gl095618
  • 发表时间:
    2022
  • 期刊:
  • 影响因子:
    5.2
  • 作者:
    Wei Yang;Hao Wei;Liang Zhao
  • 通讯作者:
    Liang Zhao

Wei Yang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('Wei Yang', 18)}}的其他基金

Collaborative Research: CCRI: Planning-C: An Infrastructure and Dataset for Research in Android Testing & Analysis
合作研究:CCRI:Planning-C:Android 测试研究的基础设施和数据集
  • 批准号:
    2235137
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
EAGER: Free Energy Sampling of Biomolecular Dynamics at Biological Timescales
EAGER:生物时间尺度上生物分子动力学的自由能采样
  • 批准号:
    1839694
  • 财政年份:
    2018
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
Who will care for you when you get old? A study of inequities in health and long-term care among the elderly in rural China
当你老了谁来照顾你?
  • 批准号:
    ES/N002717/1
  • 财政年份:
    2016
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Research Grant
Who will care for you when you get old? A study of inequities in health and long-term care among the elderly in rural China
当你老了谁来照顾你?
  • 批准号:
    ES/N002717/2
  • 财政年份:
    2016
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Research Grant
Achieving Long Timescale Sampling in Biomolecular Simulations
在生物分子模拟中实现长时间尺度采样
  • 批准号:
    1158284
  • 财政年份:
    2012
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
Achieving Long Timescale Sampling in Biomolecular Simulations
在生物分子模拟中实现长时间尺度采样
  • 批准号:
    0919983
  • 财政年份:
    2009
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
A Workshop in Plasticity and Commemorative Volume in Honor of Professor E.H. Lee
可塑性研讨会及纪念E.H.教授纪念册
  • 批准号:
    9019931
  • 财政年份:
    1990
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant

相似海外基金

Enhancing the Accuracy and Interpretability of Global Flood Models with AI: Development of a Physics-Guided Deep Learning Model Considering River Network Topology
利用人工智能提高全球洪水模型的准确性和可解释性:考虑河网拓扑的物理引导深度学习模型的开发
  • 批准号:
    24K17353
  • 财政年份:
    2024
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Grant-in-Aid for Early-Career Scientists
CAREER: Enhancing Temperature Visualization in Boiling Fluid over Finned Surfaces using Deep Learning-Enhanced Laser-Induced Fluorescence
职业:使用深度学习增强激光诱导荧光增强翅片表面沸腾流体的温度可视化
  • 批准号:
    2337973
  • 财政年份:
    2024
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Continuing Grant
RII Track-4:@NASA: Enhancing Flood Detection and Mapping by Using PolSAR, Metaheuristic, and Deep Learning Algorithms
RII Track-4:@NASA:使用 PolSAR、元启发式和深度学习算法增强洪水检测和绘图
  • 批准号:
    2327253
  • 财政年份:
    2024
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
Developing Virtual Reality-Mediated Representational Tools for Supporting and Enhancing Deep Mathematical Understanding of Linear Algebra Relationships
开发虚拟现实介导的表示工具来支持和增强对线性代数关系的深入数学理解
  • 批准号:
    2315756
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
Enhancing clinical brain MRI scans with deep learning for improved deep brain stimulation
通过深度学习增强临床脑 MRI 扫描,以改善深部脑刺激
  • 批准号:
    2897458
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Studentship
CICI: UCSS: Enhancing the Usability of Vulnerability Assessment Results for Open-Source Software Technologies in Scientific Cyberinfrastructure: A Deep Learning Perspective
CICI:UCSS:增强科学网络基础设施中开源软件技术漏洞评估结果的可用性:深度学习视角
  • 批准号:
    2319325
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Standard Grant
Enhancing personalized insights into common obstetric disorders using longitudinal deep-phenotyping data
使用纵向深度表型数据增强对常见产科疾病的个性化见解
  • 批准号:
    10723841
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
Learn, transfer, generate: Developing novel deep learning models for enhancing robustness and accuracy of small-scale single-cell RNA sequencing studies
学习、转移、生成:开发新颖的深度学习模型,以增强小规模单细胞 RNA 测序研究的稳健性和准确性
  • 批准号:
    10535708
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
Enhancing the stability of RNA Therapeutics to improve their delivery and efficacy using Deep Eutectic Solvents
使用低共熔溶剂增强 RNA 疗法的稳定性,以改善其递送和功效
  • 批准号:
    10070430
  • 财政年份:
    2023
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Collaborative R&D
Enhancing Navigation Accuracy in Autonomous Vehicles using Perception Systems and Deep learning
使用感知系统和深度学习提高自动驾驶车辆的导航精度
  • 批准号:
    559305-2021
  • 财政年份:
    2022
  • 资助金额:
    $ 52.71万
  • 项目类别:
    Alexander Graham Bell Canada Graduate Scholarships - Doctoral
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了