A survey of the landscape of potential security threats from malicious uses of artificial intelligence technologies, and propose ways to better forecast, prevent, and mitigate these threats.
This session will take a critical, deep-dive into what this means and will explore this through the following reading material with an objective to produce a short article summarizing the views from our discussions.
Readings: [Mandatory for this session - this session there won't be as much time as previous sessions (see agenda) to discuss the readings so make sure to do this before arriving]
1) Malicious Use of AI: Forecasting, Prevention and Mitigation https://arxiv.org/pdf/1802.07228.pdf
NOTE : Please join Slack via http://bit.ly/ai-ethics-signup as we will be actively discussing things there leading up to the session.
Format : [Session will start sharp 6:30 pm]
6:35-6:40 Break out into groups
6:40-7:00 Group discussion
7:00-7:55 Group presentations and debate [3 min. presentation + 4 min cross-questioning by group]
7:55-8:00 Session wrap-up