#195 – Sella Nevo on who's trying to steal frontier AI models, and what they could do with them

#195 – Sella Nevo on who's trying to steal frontier AI models, and what they could do with them

"Computational systems have literally millions of physical and conceptual components, and around 98% of them are embedded into your infrastructure without you ever having heard of them. And an inordinate amount of them can lead to a catastrophic failure of your security assumptions. And because of this, the Iranian secret nuclear programme failed to prevent a breach, most US agencies failed to prevent multiple breaches, most US national security agencies failed to prevent breaches. So ensuring your system is truly secure against highly resourced and dedicated attackers is really, really hard." —Sella Nevo

In today’s episode, host Luisa Rodriguez speaks to Sella Nevo — director of the Meselson Center at RAND — about his team’s latest report on how to protect the model weights of frontier AI models from actors who might want to steal them.

Links to learn more, highlights, and full transcript.

They cover:

  • Real-world examples of sophisticated security breaches, and what we can learn from them.
  • Why AI model weights might be such a high-value target for adversaries like hackers, rogue states, and other bad actors.
  • The many ways that model weights could be stolen, from using human insiders to sophisticated supply chain hacks.
  • The current best practices in cybersecurity, and why they may not be enough to keep bad actors away.
  • New security measures that Sella hopes can mitigate with the growing risks.
  • Sella’s work using machine learning for flood forecasting, which has significantly reduced injuries and costs from floods across Africa and Asia.
  • And plenty more.

Also, RAND is currently hiring for roles in technical and policy information security — check them out if you're interested in this field!

Chapters:

  • Cold open (00:00:00)
  • Luisa’s intro (00:00:56)
  • The interview begins (00:02:30)
  • The importance of securing the model weights of frontier AI models (00:03:01)
  • The most sophisticated and surprising security breaches (00:10:22)
  • AI models being leaked (00:25:52)
  • Researching for the RAND report (00:30:11)
  • Who tries to steal model weights? (00:32:21)
  • Malicious code and exploiting zero-days (00:42:06)
  • Human insiders (00:53:20)
  • Side-channel attacks (01:04:11)
  • Getting access to air-gapped networks (01:10:52)
  • Model extraction (01:19:47)
  • Reducing and hardening authorised access (01:38:52)
  • Confidential computing (01:48:05)
  • Red-teaming and security testing (01:53:42)
  • Careers in information security (01:59:54)
  • Sella’s work on flood forecasting systems (02:01:57)
  • Luisa’s outro (02:04:51)


Producer and editor: Keiran Harris
Audio engineering team: Ben Cordell, Simon Monsour, Milo McGuire, and Dominic Armstrong
Additional content editing: Katy Moore and Luisa Rodriguez
Transcriptions: Katy Moore

Jaksot(325)

#169 – Paul Niehaus on whether cash transfers cause economic growth, and keeping theft to acceptable levels

#169 – Paul Niehaus on whether cash transfers cause economic growth, and keeping theft to acceptable levels

"One of our earliest supporters and a dear friend of mine, Mark Lampert, once said to me, “The way I think about it is, imagine that this money were already in the hands of people living in poverty. I...

26 Loka 20231h 47min

#168 – Ian Morris on whether deep history says we're heading for an intelligence explosion

#168 – Ian Morris on whether deep history says we're heading for an intelligence explosion

"If we carry on looking at these industrialised economies, not thinking about what it is they're actually doing and what the potential of this is, you can make an argument that, yes, rates of growth a...

23 Loka 20232h 43min

#167 – Seren Kell on the research gaps holding back alternative proteins from mass adoption

#167 – Seren Kell on the research gaps holding back alternative proteins from mass adoption

"There have been literally thousands of years of breeding and living with animals to optimise these kinds of problems. But because we're just so early on with alternative proteins and there's so much ...

18 Loka 20231h 54min

#166 – Tantum Collins on what he’s learned as an AI policy insider at the White House, DeepMind and elsewhere

#166 – Tantum Collins on what he’s learned as an AI policy insider at the White House, DeepMind and elsewhere

"If you and I and 100 other people were on the first ship that was going to go settle Mars, and were going to build a human civilisation, and we have to decide what that government looks like, and we ...

12 Loka 20233h 8min

#165 – Anders Sandberg on war in space, whether civilisations age, and the best things possible in our universe

#165 – Anders Sandberg on war in space, whether civilisations age, and the best things possible in our universe

"Now, the really interesting question is: How much is there an attacker-versus-defender advantage in this kind of advanced future? Right now, if somebody's sitting on Mars and you're going to war agai...

6 Loka 20232h 48min

#164 – Kevin Esvelt on cults that want to kill everyone, stealth vs wildfire pandemics, and how he felt inventing gene drives

#164 – Kevin Esvelt on cults that want to kill everyone, stealth vs wildfire pandemics, and how he felt inventing gene drives

"Imagine a fast-spreading respiratory HIV. It sweeps around the world. Almost nobody has symptoms. Nobody notices until years later, when the first people who are infected begin to succumb. They might...

2 Loka 20233h 3min

Great power conflict (Article)

Great power conflict (Article)

Today’s release is a reading of our Great power conflict problem profile, written and narrated by Stephen Clare.If you want to check out the links, footnotes and figures in today’s article, you can fi...

22 Syys 20231h 19min

#163 – Toby Ord on the perils of maximising the good that you do

#163 – Toby Ord on the perils of maximising the good that you do

Effective altruism is associated with the slogan "do the most good." On one level, this has to be unobjectionable: What could be bad about helping people more and more?But in today's interview, Toby O...

8 Syys 20233h 7min

Suosittua kategoriassa Koulutus

rss-murhan-anatomia
voi-hyvin-meditaatiot-2
rss-narsisti
psykopodiaa-podcast
adhd-podi
rss-rahamania
rss-valo-minussa-2
rss-vapaudu-voimaasi
rss-niinku-asia-on
mielipaivakirja
rss-uskonto-on-tylsaa
aamukahvilla
rss-duodecim-lehti
ilona-rauhala
kesken
psykologia
rss-eron-alkemiaa
rss-koira-haudattuna
rss-arkea-ja-aurinkoa-podcast-espanjasta
ihminen-tavattavissa-tommy-hellsten-instituutti