The Road Toward Dependable AI Based Systems
Prof. Paolo Tonella
Università della Svizzera italiana (USI)
Switzerland
DEIB - Seminar Room "N. Schiavoni" (Bld. 20)
June 23rd, 2023
2.30 pm
Contacts:
Luciano Baresi
Research Line:
Advanced software architectures and methodologies
Università della Svizzera italiana (USI)
Switzerland
DEIB - Seminar Room "N. Schiavoni" (Bld. 20)
June 23rd, 2023
2.30 pm
Contacts:
Luciano Baresi
Research Line:
Advanced software architectures and methodologies
Sommario
On June 23rd, 2023 at 2.30 pm Prof. Paolo Tonella, Università della Svizzera italiana (USI), Switzerland, will hold a seminar on "The Road Toward Dependable AI Based Systems" in DEIB Seminar Room (Building 20).
With the advent of deep learning, AI components have achieved unprecedented performance on complex, human competitive tasks, such as image, video, text and audio processing. Hence, they are increasingly integrated into sophisticated software systems, some of which (e.g., autonomous vehicles) are required to deliver certified dependability warranties. In this talk, I will consider the unique features of AI based systems and of the faults possibly affecting them, in order to revise the testing fundamentals and redefine the overall goal of testing, taking a statistical view on the dependability warranties that can be actually delivered. Then, I will consider the key elements of a revised testing process for AI based systems, including the test oracle and the test input generation problems. I will also introduce the notion of runtime supervision, to deal with unexpected error conditions that may occur in the field. Finally, I will identify the future steps that are essential to close the loop from testing to operation, proposing an empirical framework that reconnects the output of testing to its original goals.
With the advent of deep learning, AI components have achieved unprecedented performance on complex, human competitive tasks, such as image, video, text and audio processing. Hence, they are increasingly integrated into sophisticated software systems, some of which (e.g., autonomous vehicles) are required to deliver certified dependability warranties. In this talk, I will consider the unique features of AI based systems and of the faults possibly affecting them, in order to revise the testing fundamentals and redefine the overall goal of testing, taking a statistical view on the dependability warranties that can be actually delivered. Then, I will consider the key elements of a revised testing process for AI based systems, including the test oracle and the test input generation problems. I will also introduce the notion of runtime supervision, to deal with unexpected error conditions that may occur in the field. Finally, I will identify the future steps that are essential to close the loop from testing to operation, proposing an empirical framework that reconnects the output of testing to its original goals.
Biografia
Paolo Tonella is Full Professor at the Faculty of Informatics and at the Software Institute of Università della Svizzera italiana (USI) in Lugano, Switzerland. He is Honorary Professor at University College London, UK. Paolo Tonella holds an ERC Advanced grant as Principal Investigator of the project PRECRIME. He has written over 150 peer reviewed conference papers and over 50 journal papers. In 2011 he was awarded the ICSE 2001 MIP (Most Influential Paper) award, for his paper: "Analysis and Testing of Web Applications".
His H-index (according to Google scholar) is 64. He is/was in the editorial board of TOSEM, TSE and EMSE. He is Program Co-Chair of ESEC/FSE 2023. His current research interests are in software testing, in particular approaches to ensure the dependability of machine learning based systems, automated testing of cyber physical systems, and test oracle inference and improvement.
His H-index (according to Google scholar) is 64. He is/was in the editorial board of TOSEM, TSE and EMSE. He is Program Co-Chair of ESEC/FSE 2023. His current research interests are in software testing, in particular approaches to ensure the dependability of machine learning based systems, automated testing of cyber physical systems, and test oracle inference and improvement.
