Automated Software Vulnerability Testing Using Deep Learning Methods

Kuznetsov, Alexandr; Yeromin, Yehor; Shapoval, Oleksiy; Chernov, Kyrylo; Popova, M.V.; Serdukov, Kostyantyn

doi:10.1109/ukrcon.2019.8879997

Cited by 11 publications

(2 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reason supervised learning is mostly employed in the articles could be that supervised learning models are comparatively simple and produce results with high confidence and accuracy. We also noticed that only 4 out of 263 (2%) articles [3,61,225,238] used reinforcement learning. This implies a little interest of researchers in the applications of reinforcement learning to SE.…”

Section: Relation Of Sdlc Stages With ML Typesmentioning

confidence: 91%

A Literature Review of Using Machine Learning in Software Development Life Cycle Stages

Shafiq¹,

Mashkoor

Mayr-Dorn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

The software engineering community is rapidly adopting machine learning for transitioning modern-day software towards highly intelligent and self-learning systems. However, the software engineering community is still discovering new ways how machine learning can offer help for various software development life cycle stages. In this article, we present a study on the use of machine learning across various software development life cycle stages. The overall aim of this article is to investigate the relationship between software development life cycle stages, and machine learning tools, techniques, and types. We attempt a holistic investigation in part to answer the question of whether machine learning favors certain stages and/or certain techniques.

show abstract

Section: Relation Of Sdlc Stages With ML Typesmentioning

confidence: 91%

A Literature Review of Using Machine Learning in Software Development Life Cycle Stages

Shafiq¹,

Mashkoor

Mayr-Dorn

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…ϵ-greedy method occasionally selects random events with the ϵ value probability. Commonly used epsilon values found in the literature are 0.1 [68], 0.2 [44], 0.5 [71]. An improved version of the ϵ-greedy method called decayed-ϵ-greedy utilized [75] [14] [69] in many existing studies.…”

Section: Threats To Validitymentioning

confidence: 99%

Reinforcement Learning-Based Test Case Generation with Test Suite Prioritization for Android Application Testing

Khan

View full text Add to dashboard Cite

This dissertation introduces a hybrid strategy for automated testing of Android applications that combines reinforcement learning and test suite prioritization. These approaches aim to improve the effectiveness of the testing process by employing reinforcement learning algorithms, namely Q-learning and SARSA (State-Action-Reward-State-Action), for automated test case generation. The studies provide compelling evidence that reinforcement learning techniques hold great potential in generating test cases that consistently achieve high code coverage; however, the generated test cases may not always be in the optimal order. In this study, novel test case prioritization methods are developed, leveraging pairwise event interactions coverage, application state coverage, and application activity coverage, so as to optimize the rates of code coverage specifically for SARSA-generated test cases. Additionally, test suite prioritization techniques are introduced based on UI element coverage, test case cost, and test case complexity to further enhance the ordering of SARSA-generated test cases. Empirical investigations demonstrate that applying the proposed test suite prioritization techniques to the test suites generated by the reinforcement learning algorithm SARSA improved the rates of code coverage over original orderings and random orderings of test cases.

show abstract