Neuro-symbolic artificial intelligence: The state of the art
Neuro-symbolic AI is an emerging subfield of Artificial Intelligence that brings together two
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
hitherto distinct approaches.” Neuro” refers to the artificial neural networks prominent in …
Trustworthy ai
JM Wing - Communications of the ACM, 2021 - dl.acm.org
Trustworthy AI Page 1 64 COMMUNICATIONS OF THE ACM | OCTOBER 2021 | VOL. 64 | NO.
10 review articles DOI:10.1145/3448248 The pursuit of responsible AI raises the ante on both …
10 review articles DOI:10.1145/3448248 The pursuit of responsible AI raises the ante on both …
Causality-based neural network repair
Neural networks have had discernible achievements in a wide range of applications. The
wide-spread adoption also raises the concern of their dependability and reliability. Similar to …
wide-spread adoption also raises the concern of their dependability and reliability. Similar to …
Fairness testing: A comprehensive survey and analysis of trends
Unfair behaviors of Machine Learning (ML) software have garnered increasing attention and
concern among software engineers. To tackle this issue, extensive research has been …
concern among software engineers. To tackle this issue, extensive research has been …
Information-theoretic testing and debugging of fairness defects in deep neural networks
The deep feedforward neural networks (DNNs) are increasingly deployed in socioeconomic
critical decision support software systems. DNNs are exceptionally good at finding min-imal …
critical decision support software systems. DNNs are exceptionally good at finding min-imal …
Managing bias and unfairness in data for decision support: a survey of machine learning and data engineering approaches to identify and mitigate bias and …
The increasing use of data-driven decision support systems in industry and governments is
accompanied by the discovery of a plethora of bias and unfairness issues in the outputs of …
accompanied by the discovery of a plethora of bias and unfairness issues in the outputs of …
Quantitative verification of neural networks and its security applications
Neural networks are increasingly employed in safety-critical domains. This has prompted
interest in verifying or certifying logically encoded properties of neural networks. Prior work …
interest in verifying or certifying logically encoded properties of neural networks. Prior work …
Adversarial robustness of deep neural networks: A survey from a formal verification perspective
Neural networks have been widely applied in security applications such as spam and
phishing detection, intrusion prevention, and malware detection. This black-box method …
phishing detection, intrusion prevention, and malware detection. This black-box method …
Formal specification for deep neural networks
The increasing use of deep neural networks in a variety of applications, including some
safety-critical ones, has brought renewed interest in the topic of verification of neural …
safety-critical ones, has brought renewed interest in the topic of verification of neural …