Privacy-Preserving and Explainable AI in Industrial Applications

Abstract

The industrial environment has gone through the fourth revolution, also called “Industry 4.0”, where the main aspect is digitalization. Each device employed in an industrial process is connected to a network called the industrial Internet of things (IIOT). With IIOT manufacturers being capable of tracking every device, it has become easier to prevent or quickly solve failures. Specifically, the large amount of available data has allowed the use of artificial intelligence (AI) algorithms to improve industrial applications in many ways (e.g., failure detection, process optimization, and abnormality detection). Although data are abundant, their access has raised problems due to privacy concerns of manufacturers. Censoring sensitive information is not a desired approach because it negatively impacts the AI performance. To increase trust, there is also the need to understand how AI algorithms make choices, i.e., to no longer regard them as black boxes. This paper focuses on recent advancements related to the challenges mentioned above, discusses the industrial impact of proposed solutions, and identifies challenges for future research. It also presents examples related to privacy-preserving and explainable AI solutions, and comments on the interaction between the identified challenges in the conclusions.

SpecXAI -- Spectral interpretability of Deep Learning Models

“…Explainability is also equally important for building trust, especially in several engineering applications that require Verification and Validation such as designing automotive vehicles and aircraft etc. [8][9][10][11].…”

Specxai - Spectral Interpretability of Deep Learning Models

“…While some model architectures, such as those based on attention mechanisms [1][2][3], offer a certain level of natural explanations, other deep learning models remain highly complex and challenging to interpret [4][5][6][7]. This lack of interpretability makes it difficult to comprehend how the model arrives at a particular decision, which can be especially problematic in areas like healthcare [8], finance [9,10], and other engineering sectors where transparency, trust, and verification are crucial [11][12][13][14]. Over the past decade, researchers have made some significant progress in developing methods to enhance the interpretability of deep learning models.…”