Search

Deep Learning (DL) techniques are at the heart of most future advanced software functions in Critical Autonomous AI-based Systems (CAIS), where they also represent a major competitive factor. Hence, the economic success of CAIS industries (e.g., automotive, space, railway) depends on their ability to design, implement, qualify, and certify DL-based software products under bounded effort/cost. However, there is a fundamental gap between Functional Safety (FUSA) requirements on CAIS and the nature of DL solutions. This gap stems from the development process of DL libraries and affects high-level safety concepts such as (1) explainability and traceability, (2) suitability for varying safety requirements, (3) FUSA-compliant implementations, and (4) real-time constraints. As a matter of fact, the data-dependent and stochastic nature of DL algorithms clashes with current FUSA practice, which instead builds on deterministic, verifiable, and pass/fail test-based software. The SAFEXPLAIN project tackles these challenges and targets by providing a flexible approach to allow the certification - hence adoption - of DL-based solutions in CAIS building on: (1) DL solutions that provide end-to-end traceability, with specific approaches to explain whether predictions can be trusted and strategies to reach (and prove) correct operation, in accordance to certification standards; (2) alternative and increasingly sophisticated design safety patterns for DL with varying criticality and fault tolerance requirements; (3) DL library implementations that adhere to safety requirements; and (4) computing platform configurations, to regain determinism, and probabilistic timing analyses, to handle the remaining non-determinism., The research leading to these results has received funding from the Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595. BSC authors have also been supported by the Spanish Ministry of Science and Innovation under grant PID2019- 107255GBC21/AEI/10.13039/501100011033., Peer Reviewed, "Article signat per 22 autors/es: Jaume Abella, Jon Perez, Cristofer Englund, Bahram Zonooz, Gabriele Giordana, Carlo Donzella, Francisco J. Cazorla, Enrico Mezzetti, Isabel Serra, Axel Brando, Irune Agirre, Fernando Eizaguirre, Thanh Hai Bui, Elahe Arani, Fahad Sarfraz, Ajay Balasubramaniam, Ahmed BadarIlaria Bloise, Lorenzo Feruglio, Ilaria Cinelli, Davide Brighenti, Davide Cunial", Postprint (author's final draft)

Deep Learning (DL) techniques are at the heart of most future advanced software functions in Critical Autonomous AI-based Systems (CAIS), where they also represent a major competitive factor. Hence, the economic success of CAIS industries (e.g., automotive, space, railway) depends on their ability to design, implement, qualify, and certify DL-based software products under bounded effort/cost. However, there is a fundamental gap between Functional Safety (FUSA) requirements on CAIS and the nature of DL solutions. This gap stems from the development process of DL libraries and affects high-level safety concepts such as (1) explainability and traceability, (2) suitability for varying safety requirements, (3) FUSA-compliant implementations, and (4) real-time constraints. As a matter of fact, the data-dependent and stochastic nature of DL algorithms clashes with current FUSA practice, which instead builds on deterministic, verifiable, and pass/fail test-based software. The SAFEXPLAIN project tackles these challenges and targets by providing a flexible approach to allow the certification - hence adoption - of DL-based solutions in CAIS building on: (1) DL solutions that provide end-to-end traceability, with specific approaches to explain whether predictions can be trusted and strategies to reach (and prove) correct operation, in accordance to certification standards; (2) alternative and increasingly sophisticated design safety patterns for DL with varying criticality and fault tolerance requirements; (3) DL library implementations that adhere to safety requirements; and (4) computing platform configurations, to regain determinism, and probabilistic timing analyses, to handle the remaining non-determinism. © 2023 EDAA., The research leading to these results has received funding from the Horizon Europe Programme under the SAFEXPLAIN Project (www.safexplain.eu), grant agreement num. 101069595. BSC authors have also been supported by the Spanish Ministry of Science and Innovation under grant PID2019-107255GBC21/AEI/10.13039/501100011033