LessWrong (Curated & Popular)

"Security Mindset: Lessons from 20+ years of Software Security Failures Relevant to AGI Alignment" by elspood


Listen Later

https://www.lesswrong.com/posts/Ke2ogqSEhL2KCJCNx/security-mindset-lessons-from-20-years-of-software-security


Background

I have been doing red team, blue team (offensive, defensive) computer security for a living since September 2000. The goal of this post is to compile a list of general principles I've learned during this time that are likely relevant to the field of AGI Alignment. If this is useful, I could continue with a broader or deeper exploration.

Alignment Won't Happen By Accident

I used to use the phrase when teaching security mindset to software developers that "security doesn't happen by accident." A system that isn't explicitly designed with a security feature is not going to have that security feature. More specifically, a system that isn't designed to be robust against a certain failure mode is going to exhibit that failure mode.

This might seem rather obvious when stated explicitly, but this is not the way that most developers, indeed most humans, think. I see a lot of disturbing parallels when I see anyone arguing that AGI won't necessarily be dangerous. An AGI that isn't intentionally designed not to exhibit a particular failure mode is going to have that failure mode. It is certainly possible to get lucky and not trigger it, and it will probably be impossible to enumerate even every category of failure mode, but to have any chance at all we will have to plan in advance for as many failure modes as we can possibly conceive.

As a practical enforcement method, I used to ask development teams that every user story have at least three abuser stories to go with it. For any new capability, think at least hard enough about it that you can imagine at least three ways that someone could misuse it. Sometimes this means looking at boundary conditions ("what if someone orders 2^64+1 items?"), sometimes it means looking at forms of invalid input ("what if someone tries to pay -$100, can they get a refund?"), and sometimes it means being aware of particular forms of attack ("what if someone puts Javascript in their order details?").

...more
View all episodesView all episodes
Download on the App Store

LessWrong (Curated & Popular)By LessWrong

  • 4.8
  • 4.8
  • 4.8
  • 4.8
  • 4.8

4.8

12 ratings


More shows like LessWrong (Curated & Popular)

View all
Macro Voices by Hedge Fund Manager Erik Townsend

Macro Voices

3,072 Listeners

Odd Lots by Bloomberg

Odd Lots

1,932 Listeners

EconTalk by Russ Roberts

EconTalk

4,264 Listeners

Conversations with Tyler by Mercatus Center at George Mason University

Conversations with Tyler

2,455 Listeners

Philosophy Bites by Edmonds and Warburton

Philosophy Bites

1,547 Listeners

ChinaTalk by Jordan Schneider

ChinaTalk

288 Listeners

ManifoldOne by Steve Hsu

ManifoldOne

95 Listeners

Machine Learning Street Talk (MLST) by Machine Learning Street Talk (MLST)

Machine Learning Street Talk (MLST)

96 Listeners

Dwarkesh Podcast by Dwarkesh Patel

Dwarkesh Podcast

519 Listeners

Clearer Thinking with Spencer Greenberg by Spencer Greenberg

Clearer Thinking with Spencer Greenberg

138 Listeners

Razib Khan's Unsupervised Learning by Razib Khan

Razib Khan's Unsupervised Learning

209 Listeners

"Econ 102" with Noah Smith and Erik Torenberg by Turpentine

"Econ 102" with Noah Smith and Erik Torenberg

151 Listeners

Money Stuff: The Podcast by Bloomberg

Money Stuff: The Podcast

393 Listeners

Complex Systems with Patrick McKenzie (patio11) by Patrick McKenzie

Complex Systems with Patrick McKenzie (patio11)

134 Listeners

The Marginal Revolution Podcast by Mercatus Center at George Mason University

The Marginal Revolution Podcast

96 Listeners