XAI enhancing cyber defence against adversarial attacks in industrial applications

Makridis, Georgios; Theodoropoulos, Spyros; Dardanis, Dimitrios; Makridis, Ioannis; Separdani, Maria Margarita; Fatouros, Georgios; Kyriazis, Dimosthenis; Koulouris, Panagiotis

doi:10.1109/ipas55744.2022.10052858

Cited by 6 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unintended consequences of unexplained AI in CPS include undetected bias, improper use of the system due to lack of trust, unfair results, failure to correct and update the AI-based system as flaws are discovered, security risks, lack of accountability, and lack of appropriate human oversight. Much of the recent interest in interpretability and XAI is driven by the need for accountability and transparency of AI-based decisions as well as the risks of cybersecurity attacks against AI-based cyber-physical manufacturing systems [50]. Explainable AI also helps to "minimize the cost and consequences of poor decisions" [50].…”

Section: E Risks Of Unexplainable Ai In Cpsmentioning

confidence: 99%

“…Much of the recent interest in interpretability and XAI is driven by the need for accountability and transparency of AI-based decisions as well as the risks of cybersecurity attacks against AI-based cyber-physical manufacturing systems [50]. Explainable AI also helps to "minimize the cost and consequences of poor decisions" [50]. In CPS, poor decisions can create financial loss, loss or waste of materials, products of unsatisfactory quality, failure to meet requirements, system shutdown, and accidents.…”

Section: E Risks Of Unexplainable Ai In Cpsmentioning

confidence: 99%

“…Studies have demonstrated the successful implementation of XAI for attack detection in cyber-physical systems [8], [9], [41], [50]. XAI also drives cybersecurity improvement in CPS by assuring accountability.…”

Section: E Risks Of Unexplainable Ai In Cpsmentioning

confidence: 99%

See 2 more Smart Citations

Explainable AI for Cyber-Physical Systems: Issues and Challenges

Hoenig,

Roy,

Acquaah

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Artificial intelligence and cyber-physical systems (CPS) are two of the key technologies of the future that are enabling major global shifts. However, most of the current implementations of AI in CPS are not explainable, which creates serious problems in ethical, legal, regulatory, and other domains. Therefore, it is necessary for explainable artificial intelligence (XAI) to be integrated with cyber-physical systems to meet the vital needs for control, fairness, accountability, safety, cyber-resilience, and cybersecurity. The goal of this review is to demonstrate the need, benefits, challenges, and implementation of XAI for CPS. We review the existing literature about XAI and CPS, discuss the current state of the art, examine applications in different domains, and make recommendations for future research directions. To the best of our knowledge, this is the first peer-reviewed academic article to provide a comprehensive review of general XAI for CPS. We also contribute new research ideas including development of multisensory explanations and outputs for these systems, application of XAI to CPS to decrease occupational burnout and increase employee engagement, and enumeration of the multidisciplinary goals and benefits of XAI as applied to cyber-physical systems.

show abstract

Section: E Risks Of Unexplainable Ai In Cpsmentioning

confidence: 99%

Section: E Risks Of Unexplainable Ai In Cpsmentioning

confidence: 99%