Trustworthy AI: Towards Auditable AI Systems | AI FOR GOOD DISCOVERY
Artificial Intelligence (AI) systems such as deep neural networks play a growing role as part of decision and control systems in a plethora of applications. While some of these applications are safety- and security-critical, the use of AI systems pose new challenges with regard to aspects such as IT security, safety, robustness and trustworthiness. To meet these challenges, a generally agreed-upon framework for auditing AI systems throughout their life cycle, comprising evaluation strategies, tools and standards, is required. This is under development but, as of now, only partly ready for practical use. In this talk, focusing on the applications domains autonomous driving and biometrics, the current status of AI system auditing is presented together with open questions and future directions.
SHOWNOTES
00:00 Intro: Trustworthy AI: Towards Auditable AI Systems
04:00 Responsibilities of BSI in the context of AI
04:30 What is the role of BSI in the context of AI?
05:00 AI systems are connected and embedded in safety and security-critical applications
06:00 CAI differs qualitatively from cIT and sAI
08:00 Connectionist AI (cAI) specific and qualitatively new problems
09:00 Embedded nature of cAI
10:00 IT security of systems
12:00 Vulnerability of cAI systems
15:00 AI-specific attacks on road systems
17:00 Adversarial attacks
19:00 What kind of measures of defence are there?
22:00 Test and improvements of the robustness of neural networks
26:00 AI System development process
30:00 Open Challenges: What should be the communication between developer and users?
35:00 How to achieve acceptable levels of security, safety, audit quality
Use of research and development.
Take into consideration favourable boundary conditions.
40:00 Start of Q&A
41:00 Question: can we embed an insecure system in a secure environment, and will that be secure?
Website: https://aiforgood.itu.int/
Twitter: https://twitter.com/ITU_AIForGood
LinkedIn Page: https://www.linkedin.com/company/26511907
LinkedIn Group: https://www.linkedin.com/groups/8567748
Instagram: https://www.instagram.com/aiforgood
Facebook: https://www.facebook.com/AIforGood