English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The reliability of software that has a Deep Neural Network (DNN) as acomponent is urgently important today given the increasing number of criticalapplications being deployed with DNNs. The need for reliability raises a needfor rigorous testing of the safety and trustworthiness of these systems. In thelast few years, there have been a number of research efforts focused on testingDNNs. However the test generation techniques proposed so far lack a check todetermine whether the test inputs they are generating are valid, and thusinvalid inputs are produced. To illustrate this situation, we explored threerecent DNN testing techniques. Using deep generative model based inputvalidation, we show that all the three techniques generate significant numberof invalid test inputs. We further analyzed the test coverage achieved by thetest inputs generated by the DNN testing techniques and showed how invalid testinputs can falsely inflate test coverage metrics.  To overcome the inclusion of invalid inputs in testing, we propose atechnique to incorporate the valid input space of the DNN model under test inthe test generation process. Our technique uses a deep generative model-basedalgorithm to generate only valid inputs. Results of our empirical studies showthat our technique is effective in eliminating invalid tests and boosting thenumber of valid test inputs generated.

Distribution-Aware Testing of Neural Networks Using Generative Models