Trustworthy AI: Towards Auditable AI Systems | AI FOR GOOD DISCOVERY

Channel:
Subscribers:
19,800
Published on ● Video Link: https://www.youtube.com/watch?v=JoCYswcRHRU



Duration: 0:00
344 views
0


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




Other Videos By AI for Good


2021-04-28Trustworthy AI: Adversarial Attacks and Defences | AI FOR GOOD DISCOVERY
2021-04-26Satellite Data Analysis and Machine Learning Classification with QGIS Part 1 | AI FOR GOOD WEBINARS
2021-04-26Geospatial AI/ML Applications and Policies – A Global Perspective | AI FOR GOOD WEBINARS
2021-04-26AI for Heart Attack Prevention | AI FOR GOOD
2021-04-25Towards Autonomous 6G Networks and the Role of Advanced ML Techniques | AI/ML in 5G Challenge
2021-04-22AI for Good 2020 Highlights | AI FOR GOOD
2021-04-21Trustworthy AI: Steps Toward Trustworthy Machine Learning | AI FOR GOOD DISCOVERY
2021-04-20Malware and Machine Learning – A Match Made in Hell | Mikko Hyppönen | AI for Good
2021-04-202021 Live Pitching Session 1 | AI FOR GOOD INNOVATION FACTORY
2021-04-19Creating Safe Digital Spaces for all Through Esports and AI | AI FOR GOOD WEBINARS
2021-04-14Trustworthy AI: Towards Auditable AI Systems | AI FOR GOOD DISCOVERY
2021-04-07Crowdsourcing AI for Future Resilience Part 2 | AI FOR GOOD WEBINARS
2021-04-06AI for sustainable transformation in smart cities, mobility & energy | AI FOR GOOD WEBINARS
2021-03-30Trustworthy AI: Adversarially (non-)Robust ML | Nicholas Carlini Google AI | AI FOR GOOD DISCOVERY
2021-03-22AI for Good in Action – Crowdsourcing AI for Future Resilience | AI FOR GOOD WEBINARS
2021-03-18Jean-Philippe Courtois | President Microsoft Global Sales | AI FOR GOOD GLOBAL SUMMIT 2019 ARCHIVES
2021-03-18Towards transparency in AI: methods and challenges | Timnit Gebru | Co-founder of Black in AI
2021-03-18Jim Hagemann Snabe | Chairman at Siemens and Maersk | AI FOR GOOD GLOBAL SUMMIT 2019 ARCHIVES
2021-03-18Yves Daccord | International Committee of the Red Cross | AI FOR GOOD GLOBAL SUMMIT 2019 ARCHIVES
2021-03-18Crowdsourcing AI for Future Resilience | AI FOR GOOD WEBINARS
2021-03-18Let's talk - Protecting Life after War and Conflict: AI for Weapon Decontamination