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：
Wei Yang
金额：
$ 52.71万
依托单位：
University of Texas at Dallas
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

来源：
https://www.nsf.gov/awardsearch/showAward?AWD_ID=2146443&HistoricalAwards=false
关键词：
CAREER Enhancing Deep Learning based

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.

该奖项的全部或部分资金来源于《2021 年美国救援计划法案》（公法 117-2）。随着开源存储库中数百万个程序的可用性不断增加，人们提出了许多利用深度学习的技术然而，由于多种原因，所提出的深度学习模型仍然面临着许多超出模型处理能力的输入程序。（例如，程序代码的演变）。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程序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）往往是简单化和简化的，而深度学习模型可能是不透明的和过度拟合的，如果能够以某种方式将两个世界的优点结合起来，许多现有的挑战将会消失。该提案旨在在这种组合上取得进展，其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。具体来说，现有的深度学习面临两个主要问题。处理代码数据的学习模型：（1）缺乏对代码数据固有性质的理解，（2）缺乏软件工程任务的特定领域知识为了解决这些基本限制，该项目建议设计一个通用的、从短期来看，这个项目是基于用户驱动的学习框架。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采用。从长远来看，该项目有可能从根本上改变软件工程应用中基于学习的代码分析技术。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力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

DOI：
10.1145/3510003.3510088
发表时间：
2022-02
期刊：
2022 IEEE/ACM 44th International Conference on Software Engineering (ICSE)
影响因子：
0
作者：
Mirazul Haque;Yaswanth Yadlapalli;Wei Yang;Cong Liu
通讯作者：
Mirazul Haque;Yaswanth Yadlapalli;Wei Yang;Cong Liu

DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks

DOI：
10.1145/3551349.3561158
发表时间：
2022-10
期刊：
Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering
影响因子：
0
作者：
Simin Chen;Mirazul Haque;Cong Liu;Wei Yang
通讯作者：
Simin Chen;Mirazul Haque;Cong Liu;Wei Yang

NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

DOI：
10.1109/cvpr52688.2022.01493
发表时间：
2022-03
期刊：
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
影响因子：
0
作者：
Simin Chen;Zihe Song;Mirazul Haque;Cong Liu;Wei Yang
通讯作者：
Simin Chen;Zihe Song;Mirazul Haque;Cong Liu;Wei Yang

NMTSloth: understanding and testing efficiency degradation of neural machine translation systems

DOI：
10.1145/3540250.3549102
发表时间：
2022-10
期刊：
Proceedings of the 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering
影响因子：
0
作者：
Simin Chen;Cong Liu;Mirazul Haque;Zihe Song;Wei Yang
通讯作者：
Simin Chen;Cong Liu;Mirazul Haque;Zihe Song;Wei Yang