#95 – Dawn Song: Adversarial Machine Learning and Computer Security
May 12, 2020
2 hr 13 min
95
Full
94 of 498
Episode 95 · May 12, 2020
#95 – Dawn Song: Adversarial Machine Learning and Computer Security
0:00 / 2:13:04
Excerpt playback isn’t available for this episode — use the full-episode link.
Search the Record
Moment search isn’t open for this episode yet
When it opens, you’ll be able to type any phrase and jump straight to the second it was said.
Lex Fridman Episodes Around May 12, 2020
Episode 94 of 498 — walk the feed in the order it was published.
#81 – Anca Dragan: Human-Robot Interaction and Reward Engineering
#92 – Harry Cliff: Particle Physics and the Large Hadron Collider
#95 – Dawn Song: Adversarial Machine Learning and Computer Security
Summary
<p>Dawn Song is a professor of computer science at UC Berkeley with research interests in security, most recently with a focus on the intersection between computer security and machine learning.</p>
<p>Support this podcast by signing up with these sponsors:<br />
– Cash App – use code “LexPodcast” and download:<br />
– Cash App (App Store): <a href="https://apple.co/2sPrUHe">https://apple.co/2sPrUHe</a><br />
– Cash App (Google Play): <a href="https://bit.ly/2MlvP5w">https://bit.ly/2MlvP5w</a></p>
<p>EPISODE LINKS:<br />
Dawn’s Twitter: <a href="https://twitter.com/dawnsongtweets">https://twitter.com/dawnsongtweets</a><br />
Dawn’s Website: <a href="https://people.eecs.berkeley.edu/~dawnsong/">https://people.eecs.berkeley.edu/~dawnsong/</a><br />
Oasis Labs: <a href="https://www.oasislabs.com">https://www.oasislabs.com</a></p>
<p><span style="font-weight: 400;">This conversation is part of the Artificial Intelligence podcast.</span> If you would like to get more information about this podcast go to <a href="https://lexfridman.com/ai">https://lexfridman.com/ai</a> or connect with @lexfridman on <a href="https://twitter.com/lexfridman">Twitter</a>, <a href="https://www.linkedin.com/in/lexfridman/">LinkedIn</a>, <a href="https://www.facebook.com/lexfridman">Facebook</a>, <a href="https://medium.com/@lexfridman">Medium</a>, or <a href="https://www.youtube.com/lexfridman">YouTube</a> where you can watch the video versions of these conversations. If you enjoy the podcast, please rate it 5 stars on <a href="https://podcasts.apple.com/us/podcast/artificial-intelligence/id1434243584">Apple Podcasts</a>, follow on <a href="https://open.spotify.com/show/2MAi0BvDc6GTFvKFPXnkCL">Spotify</a>, or support it on <a href="https://www.patreon.com/lexfridman">Patreon</a>.</p>
<p>Here’s the outline of the episode. On some podcast players you should be able to click the timestamp to jump to that time.</p>
<p>OUTLINE:<br />
00:00 – Introduction<br />
01:53 – Will software always have security vulnerabilities?<br />
09:06 – Human are the weakest link in security<br />
16:50 – Adversarial machine learning<br />
51:27 – Adversarial attacks on Tesla Autopilot and self-driving cars<br />
57:33 – Privacy attacks<br />
1:05:47 – Ownership of data<br />
1:22:13 – Blockchain and cryptocurrency<br />
1:32:13 – Program synthesis<br />
1:44:57 – A journey from physics to computer science<br />
1:56:03 – US and China<br />