Artificial Intelligence Safety and Cybersecurity: a Timeline of AI Failures

10/25/2016
by   Roman V. Yampolskiy, et al.
1

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 the system; the goal of AI Safety is to make sure zero attacks succeed in bypassing the safety mechanisms. Unfortunately, such a level of performance is unachievable. Every security system will eventually fail; there is no such thing as a 100 system.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

02/29/2020

On Safety Assessment of Artificial Intelligence

In this paper we discuss how systems with Artificial Intelligence (AI) c...
07/18/2020

AI Failures: A Review of Underlying Issues

Instances of Artificial Intelligence (AI) systems failing to deliver con...
07/15/2019

Classification Schemas for Artificial Intelligence Failures

In this paper we examine historical failures of artificial intelligence ...
11/17/2020

Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database

Mature industrial sectors (e.g., aviation) collect their real world fail...
12/11/2019

Founding The Domain of AI Forensics

With the widespread integration of AI in everyday and critical technolog...
09/10/2012

Safe and Stabilizing Distributed Multi-Path Cellular Flows

We study the problem of distributed traffic control in the partitioned p...
04/22/2021

Understanding and Avoiding AI Failures: A Practical Guide

As AI technologies increase in capability and ubiquity, AI accidents are...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.