A survey of safety and trustworthiness of deep neural networks: Verification, testing, adversarial attack and defence, and interpretability
In the past few years, significant progress has been made on deep neural networks (DNNs)
in achieving human-level performance on several long-standing tasks. With the broader …
in achieving human-level performance on several long-standing tasks. With the broader …
[HTML][HTML] Testing machine learning based systems: a systematic mapping
Abstract Context: A Machine Learning based System (MLS) is a software system including
one or more components that learn how to perform a task from a given data set. The …
one or more components that learn how to perform a task from a given data set. The …
[HTML][HTML] A survey of safety and trustworthiness of large language models through the lens of verification and validation
Large language models (LLMs) have exploded a new heatwave of AI for their ability to
engage end-users in human-level conversations with detailed and articulate answers across …
engage end-users in human-level conversations with detailed and articulate answers across …
Machine learning testing: Survey, landscapes and horizons
This paper provides a comprehensive survey of techniques for testing machine learning
systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing …
systems; Machine Learning Testing (ML testing) research. It covers 144 papers on testing …
Software engineering for AI-based systems: a survey
AI-based systems are software systems with functionalities enabled by at least one AI
component (eg, for image-, speech-recognition, and autonomous driving). AI-based systems …
component (eg, for image-, speech-recognition, and autonomous driving). AI-based systems …
Deephunter: a coverage-guided fuzz testing framework for deep neural networks
The past decade has seen the great potential of applying deep neural network (DNN) based
software to safety-critical scenarios, such as autonomous driving. Similar to traditional …
software to safety-critical scenarios, such as autonomous driving. Similar to traditional …
Assuring the machine learning lifecycle: Desiderata, methods, and challenges
R Ashmore, R Calinescu, C Paterson - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Machine learning has evolved into an enabling technology for a wide range of highly
successful applications. The potential for this success to continue and accelerate has placed …
successful applications. The potential for this success to continue and accelerate has placed …
Tensorfuzz: Debugging neural networks with coverage-guided fuzzing
Neural networks are difficult to interpret and debug. We introduce testing techniques for
neural networks that can discover errors occurring only for rare inputs. Specifically, we …
neural networks that can discover errors occurring only for rare inputs. Specifically, we …
A software engineering perspective on engineering machine learning systems: State of the art and challenges
G Giray - Journal of Systems and Software, 2021 - Elsevier
Context: Advancements in machine learning (ML) lead to a shift from the traditional view of
software development, where algorithms are hard-coded by humans, to ML systems …
software development, where algorithms are hard-coded by humans, to ML systems …
Testing deep neural networks
Deep neural networks (DNNs) have a wide range of applications, and software employing
them must be thoroughly tested, especially in safety-critical domains. However, traditional …
them must be thoroughly tested, especially in safety-critical domains. However, traditional …