Automated Performance Testing Based on Active Deep Learning

Abstract

Generating tests that can reveal performance issues in large and complex software systems within a reasonable amount of time is a challenging task. On one hand, there are numerous combinations of input data values to explore. On the other hand, we have a limited test budget to execute tests. What makes this task even more difficult is the lack of access to source code and the internal details of these systems. In this paper, we present an automated test generation method called ACTA for black-box performance testing. ACTA is based on active learning, which means that it does not require a large set of historical test data to learn about the performance characteristics of the system under test. Instead, it dynamically chooses the tests to execute using uncertainty sampling. ACTA relies on a conditional variant of generative adversarial networks, and facilitates specifying performance requirements in terms of conditions and generating tests that address those conditions. We have evaluated ACTA on a benchmark web application, and the experimental results indicate that this method is comparable with random testing, and two other machine learning methods, i.e. PerfXRL and DN.

A Hierarchical Deep Neural Network for Detecting Lines of Codes with Vulnerabilities

“…code similaritybased methods [5]- [8], pattern-based methods [9]- [11], etc. Machine learning-based approaches, including deep learning approaches, belong to the second category [1], [12], [13]. These approaches look for patterns of vulnerabilities in the source codes and are able to generalize these patterns to unseen vulnerabilities.…”

DELFASE: A Deep Learning Method for Fault Space Exploration

“…In this paper, we propose to apply Generative Adversarial Networks (GANs) [10] to the problem of fault space exploration. GANs have been successfully used in several applications (e.g., image generation [11], anomaly detection [12] and performance testing [13]). However, to the best of our knowledge, this work demonstrates the first application of GANs in fault space exploration.…”