Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures

📖 Description

Artificial Intelligence Safety and Cybersecurity : a Timeline of AI Failures Roman V. Yampolskiy Computer Engineering and Computer Science University of Louisville [email removed] M. S. Spellchecker Microsoft Corporation One Microsoft Way , Redmond, WA [email removed] Abstract In this work , we present and analyze reported failures of artificial ly intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI fail ures will steadily increase. AI Safety can be improved based on ideas developed by cybersecurity experts . For narrow AI s safety failures are at the same , moderate, level of criticality as in cybersecurity, however for general AI, failures have a fundamentally different impact . A single failure of a superintelligent system may cause a catastrophic event without a chance for recover y. The goal of cybersecurity is to reduce the num...

📊 Game Impacts

💭 Reactions

🔗 Sources

• [1] https://arxiv.org/abs/1610.07997