'Hypothetical scenario:
Jackie logs into the admin console for the CleanSecure robot that she manages; operating on a verified kernel, it is guaranteed by the manufacturer to be hack-proof. She then uploads photographs of a new employee so …
'Hypothetical scenario:
Jackie logs into the admin console for the CleanSecure robot that she manages; operating on a verified kernel, it is guaranteed by the manufacturer to be hack-proof. She then uploads photographs of a new employee so the robot will recognize him when he walks into the building and will not sound the alarm. While she waits for the robot to authenticate its updated person database with the company’s other security systems, Jackie plays with the model train on her desk, allowing herself a couple of runs around the track that encircles her keyboard and monitor. There’s a ping, signaling successful authentication, and she smiles to herself and carries on with her tasks. Later that afternoon, Jackie is browsing Facebook while idly managing a firmware update of the robot. An ad catches her eye - a model train set sale at a hobbyist shop that, it turns out, is located just a few minutes from her house. She fills out an online form to get a brochure emailed to her, then she opens the brochure when it pops into her inbox. The robot dings, signalling a need for attention, so she minimizes the brochure and logs back into the admin console. Jackie doesn’t know that the brochure was infected with malware. Based on data from her online profile and other public info, an AI system was used to generate a very personalized vulnerability profile for Jackie - the model train advert - which was then farmed out to a freelancer to create a tailored exploit for this vulnerability. When Jackie logged into the console, her username and password were exfiltrated to a darknet command and control server. It won’t be long before someone buys them and uses them to subvert the CleanSecure robot with fully privileged access.'
- from "The Malicious Use of AI: Forecasting, Prevention, and Mitigation" (Collaborative report produced by University of Oxford, University of Cambridge, Electronic Frontier Foundation, OpenAI and others, first released Feb 2018)
++++++++++++++++++++++++++++++++
Timestamps:
00:00:00 "But How Does ChatGPT Actually Work?", Till Musshof, 13 December 2022
https://www.youtube.com/watch?v=aQguO9IeQWE
00:10:06 "But what is a neural network? | Chapter 1, Deep learning", 3Blue1Brown, 6 October 2017
https://www.youtube.com/watch?v=aircAruvnKk
00:26:08 "How ChatGPT actually works", Assembly AI, 24 January 2023
https://www.youtube.com/watch?v=x_bw_IHjCWU
00:32:19 "How ChatGPT Works Technically For Beginners", Kurdiez Space, 5 February 2023
https://www.youtube.com/watch?v=uCIa6V4uF84
