publication . Preprint . 2016

Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures

Yampolskiy, Roman V.; Spellchecker, M. S.;
Open Access English
  • Published: 25 Oct 2016
Abstract
In this work, we present and analyze reported failures of artificially intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI failures will steadily increase. AI Safety can be improved based on ideas developed by cybersecurity experts. For narrow AIs 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 recovery. The goal of cybersecurity is to reduce the number of successful attacks on th...
Subjects
free text keywords: Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Download from

[1] R. V. Yampolskiy, "Taxonomy of Pathways to Dangerous Artificial Intelligence," in Workshops at the Thirtieth AAAI Conference on Artificial Intelligence, 2016.

[2] F. Pistono and R. V. Yampolskiy, "Unethical Research: How to Create a Malevolent Artificial Intelligence," presented at the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). Ethics for Artificial Intelligence Workshop (AI-Ethics-2016), New York, NY, July 9, 2016.

Abstract
In this work, we present and analyze reported failures of artificially intelligent systems and extrapolate our analysis to future AIs. We suggest that both the frequency and the seriousness of future AI failures will steadily increase. AI Safety can be improved based on ideas developed by cybersecurity experts. For narrow AIs 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 recovery. The goal of cybersecurity is to reduce the number of successful attacks on th...
Subjects
free text keywords: Computer Science - Artificial Intelligence, Computer Science - Computers and Society
Download from

[1] R. V. Yampolskiy, "Taxonomy of Pathways to Dangerous Artificial Intelligence," in Workshops at the Thirtieth AAAI Conference on Artificial Intelligence, 2016.

[2] F. Pistono and R. V. Yampolskiy, "Unethical Research: How to Create a Malevolent Artificial Intelligence," presented at the 25th International Joint Conference on Artificial Intelligence (IJCAI-16). Ethics for Artificial Intelligence Workshop (AI-Ethics-2016), New York, NY, July 9, 2016.

Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue