Sveriges mest populära poddar
Machine Learning Street Talk (MLST)
Teknologi

#48 Machine Learning Security - Andy Smith

37 min•16 mars 2021

First episode in a series we are doing on ML DevOps. Starting with the thing which nobody seems to be talking about enough, security! We chat with cyber security expert Andy Smith about threat modelling and trust boundaries for an ML DevOps system. 

Intro [00:00:00]

ML DevOps - a security perspective [00:00:50]

Threat Modelling [00:03:03]

Adversarial examples? [00:11:27]

Nobody understands the whole stack [00:13:53]

On the size of the state space, the element of unpredictability [00:18:32]

Threat modelling in more detail [00:21:17]

Trust boundaries for an ML DevOps system [00:25:45]


Andy has a YouTube channel on cyber security! Check it out @ 

https://www.youtube.com/channel/UCywP24ly6h6NTusX88TQKTQ

https://www.linkedin.com/in/andysmith-uk/


Video version:

https://youtu.be/7Tz-3S4lypI

Fler avsnitt av Machine Learning Street Talk (MLST)

Visa alla avsnitt av Machine Learning Street Talk (MLST)
When AI Discovers The Next Transformer - Robert Lange (Sakana)
•1 tim 18 min
"Vibe Coding is a Slot Machine" - Jeremy Howard
•1 tim 27 min
Evolution "Doesn't Need" Mutation - Blaise Agüera y Arcas
•56 min
VAEs Are Energy-Based Models? [Dr. Jeff Beck]
•47 min
Abstraction & Idealization: AI's Plato Problem [Mazviita Chirimuuta]
•54 min
Why Every Brain Metaphor in History Has Been Wrong [SPECIAL EDITION]
•42 min
Bayesian Brain, Scientific Method, and Models [Dr. Jeff Beck]
•1 tim 17 min
Your Brain is Running a Simulation Right Now [Max Bennett]
•3 tim 17 min
The 3 Laws of Knowledge [César Hidalgo]
•1 tim 37 min
"I Desperately Want To Live In The Matrix" - Dr. Mike Israetel
•2 tim 56 min

Machine Learning Street Talk (MLST) med Machine Learning Street Talk (MLST) finns tillgänglig på flera plattformar. Informationen på denna sida kommer från offentliga podd-flöden.