RSS

In­for­ma­tion security

TagLast edit: Dec 22, 2022, 10:22 AM by MichaelA🔸

Information security is the set of methods aimed at protecting the confidentiality, availability and integrity of information.

Further reading

Ladish, Jeffrey & Lennart Heim (2022) Information security considerations for AI and the long term future, Effective Altruism Forum, May 2.

Wiblin, Robert & Keiran Harris (2022) Nova DasSarma on why information security may be critical to the safe development of AI systems, 80,000 Hours, June 14.

Zabel, Claire & Luke Muehlhaeuser (2019) Information security careers for GCR reduction, Effective Altruism Forum, June 20.

External links

Information Security in Effective Altruism. A group for members of the effective altruism community interested in applying information security to global catastrophic risk reduction or other areas of effective altruism.

Related entries

AI governance | AI risk | armed conflict | autonomous weapon | existential risk factor | information hazard | nuclear warfare | public interest technology

EA In­fosec: skill up in or make a tran­si­tion to in­fosec via this book club

Jason ClintonMar 5, 2023, 9:02 PM
170 points
16 comments2 min readEA link

In­for­ma­tion se­cu­rity con­sid­er­a­tions for AI and the long term future

Jeffrey LadishMay 2, 2022, 8:53 PM
134 points
8 comments11 min readEA link

80,000 Hours ca­reer re­view: In­for­ma­tion se­cu­rity in high-im­pact areas

80000_HoursJan 16, 2023, 12:45 PM
56 points
10 comments11 min readEA link
(80000hours.org)

AI com­pa­nies are not on track to se­cure model weights

Jeffrey LadishJul 18, 2024, 3:13 PM
73 points
3 comments19 min readEA link

In­for­ma­tion se­cu­rity ca­reers for GCR reduction

ClaireZabelJun 20, 2019, 11:56 PM
187 points
35 comments8 min readEA link

We need non-cy­ber­se­cu­rity peo­ple [too]

JarrahMay 5, 2024, 12:11 AM
32 points
0 comments2 min readEA link

In­for­ma­tion se­cu­rity: Be­come a hacker, not a consultant

Hans Waschke-WischedagFeb 26, 2022, 2:24 PM
54 points
10 comments6 min readEA link

AI, Cy­ber­se­cu­rity, and Malware: A Shal­low Re­port [Tech­ni­cal]

Madhav MalhotraMar 31, 2023, 12:03 PM
4 points
0 comments9 min readEA link

A short con­ver­sa­tion I had with Google Gem­ini on the dan­gers of un­reg­u­lated LLM API use, while mildly drunk in an air­port.

EvanMcCormickDec 17, 2024, 12:25 PM
1 point
0 comments8 min readEA link

Hash­marks: Pri­vacy-Pre­serv­ing Bench­marks for High-Stakes AI Evaluation

Paul BricmanDec 4, 2023, 7:41 AM
4 points
0 comments16 min readEA link
(arxiv.org)

Fix­ing In­sider Threats in the AI Sup­ply Chain

Madhav MalhotraOct 7, 2023, 10:49 AM
9 points
2 comments5 min readEA link

[Question] I’m in­ter­view­ing Nova Das Sarma about AI safety and in­for­ma­tion se­cu­rity. What shouId I ask her?

Robert_WiblinMar 25, 2022, 3:38 PM
17 points
13 comments1 min readEA link

Cy­ber­se­cu­rity of Fron­tier AI Models: A Reg­u­la­tory Review

Deric ChengApr 25, 2024, 2:51 PM
9 points
1 comment8 min readEA link

Prevent­ing AI Mi­suse: State of the Art Re­search and its Flaws

Madhav MalhotraApr 23, 2023, 10:50 AM
24 points
2 comments11 min readEA link

[Question] How to nav­i­gate po­ten­tial infohazards

more better Mar 4, 2023, 9:28 PM
16 points
7 comments1 min readEA link

AI, Cy­ber­se­cu­rity, and Malware: A Shal­low Re­port [Gen­eral]

Madhav MalhotraMar 31, 2023, 12:01 PM
5 points
0 comments8 min readEA link

[Question] De­sign­ing user au­then­ti­ca­tion pro­to­cols

Kinoshita Yoshikazu (pseudonym)Mar 13, 2023, 3:56 PM
−1 points
2 comments1 min readEA link

EA Fo­rum Prize: Win­ners for June 2019

Aaron Gertler 🔸Jul 25, 2019, 8:36 AM
32 points
15 comments4 min readEA link

Now is a good time to up­date your threat model

Flo 🔸Mar 22, 2025, 9:11 PM
29 points
0 comments1 min readEA link

Time-stamp­ing: An ur­gent, ne­glected AI safety measure

Axel SvenssonJan 30, 2023, 11:21 AM
57 points
27 comments3 min readEA link

Wor­ri­some Trends for Digi­tal Mind Evaluations

Derek ShillerFeb 20, 2025, 3:35 PM
72 points
10 comments8 min readEA link

CSER and FHI ad­vice to UN High-level Panel on Digi­tal Co­op­er­a­tion

HaydnBelfieldMar 8, 2019, 8:39 PM
22 points
7 comments6 min readEA link
(www.cser.ac.uk)

Tech­nolog­i­cal de­vel­op­ments that could in­crease risks from nu­clear weapons: A shal­low review

MichaelA🔸Feb 9, 2023, 3:41 PM
79 points
3 comments5 min readEA link
(bit.ly)

[Cause Ex­plo­ra­tion Prizes] Fund­ing to Severely Abate Phish­ing Scams

AJ ShahAug 28, 2022, 7:15 AM
5 points
0 comments2 min readEA link

Civil di­s­obe­di­ence op­por­tu­nity—a way to help re­duce chance of hard take­off from re­cur­sive self im­prove­ment of code

JonCefaluMar 25, 2023, 10:37 PM
−5 points
0 comments1 min readEA link
(codegencodepoisoningcontest.cargo.site)

My Ca­reer De­ci­sion-Mak­ing Process

ShayBenMosheJan 21, 2021, 8:17 PM
103 points
17 comments31 min readEA link

16 Re­cent Publi­ca­tions on Ex­is­ten­tial Risk (Nov & Dec 2019 up­date)

HaydnBelfieldJan 15, 2020, 12:07 PM
21 points
0 comments8 min readEA link

CSER Ad­vice to EU High-Level Ex­pert Group on AI

HaydnBelfieldMar 8, 2019, 8:42 PM
14 points
0 comments5 min readEA link
(www.cser.ac.uk)

An­nounc­ing the Ex­is­ten­tial In­foSec Forum

calebpJul 7, 2023, 9:08 PM
90 points
1 comment2 min readEA link

Some promis­ing ca­reer ideas be­yond 80,000 Hours’ pri­or­ity paths

Arden KoehlerJun 26, 2020, 10:34 AM
142 points
28 comments15 min readEA link

Reli­a­bil­ity, Se­cu­rity, and AI risk: Notes from in­fosec text­book chap­ter 1

AkashApr 7, 2023, 3:47 PM
15 points
0 comments1 min readEA link

UK policy and poli­tics careers

weeatquinceSep 28, 2019, 4:18 PM
28 points
10 comments7 min readEA link

How likely is a nu­clear ex­change be­tween the US and Rus­sia?

Luisa_RodriguezJun 20, 2019, 1:49 AM
80 points
13 comments14 min readEA link

Jobs that can help with the most im­por­tant century

Holden KarnofskyFeb 12, 2023, 6:19 PM
57 points
2 comments32 min readEA link
(www.cold-takes.com)

How CISA can Sup­port the Se­cu­rity of Large AI Models Against Theft [Grad School As­sign­ment]

Marcel DMay 3, 2023, 3:36 PM
7 points
0 comments13 min readEA link

AI Gover­nance: Op­por­tu­nity and The­ory of Impact

Allan DafoeSep 17, 2020, 6:30 AM
262 points
19 comments12 min readEA link

Fi­nal Re­port of the Na­tional Se­cu­rity Com­mis­sion on Ar­tifi­cial In­tel­li­gence (NSCAI, 2021)

MichaelA🔸Jun 1, 2021, 8:19 AM
51 points
3 comments4 min readEA link
(www.nscai.gov)

Ques­tions for fur­ther in­ves­ti­ga­tion of AI diffusion

Ben CottierDec 21, 2022, 1:50 PM
28 points
0 comments11 min readEA link

Dis­rupt­ing mal­i­cious uses of AI by state-af­fili­ated threat actors

Agustín Covarrubias 🔸Feb 14, 2024, 9:28 PM
22 points
1 comment1 min readEA link
(openai.com)

Drivers of large lan­guage model diffu­sion: in­cre­men­tal re­search, pub­lic­ity, and cascades

Ben CottierDec 21, 2022, 1:50 PM
21 points
0 comments29 min readEA link

Baobao Zhang: How so­cial sci­ence re­search can in­form AI governance

EA GlobalJan 22, 2021, 3:10 PM
9 points
0 comments16 min readEA link
(www.youtube.com)

Pri­vacy as a Blind Spot: Are There Long Term Harms in Us­ing Face­book, Google, Slack etc.?

Flo 🔸Jan 16, 2021, 5:15 PM
50 points
17 comments12 min readEA link

A New X-Risk Fac­tor: Brain-Com­puter Interfaces

JackAug 10, 2020, 10:24 AM
76 points
12 comments42 min readEA link

AGI safety and los­ing elec­tric­ity/​in­dus­try re­silience cost-effectiveness

Ross_TiemanNov 17, 2019, 8:42 AM
31 points
10 comments37 min readEA link

Kevin Esvelt: Miti­gat­ing catas­trophic biorisks

EA GlobalSep 3, 2020, 6:11 PM
32 points
0 comments22 min readEA link
(www.youtube.com)

Should there be just one west­ern AGI pro­ject?

rosehadsharDec 4, 2024, 2:41 PM
49 points
3 comments1 min readEA link
(www.forethought.org)

Why do we post our AI safety plans on the In­ter­net?

Peter S. ParkOct 31, 2022, 4:27 PM
15 points
22 comments11 min readEA link

In­tro to Cy­ber­biose­cu­rity—Kathryn Millet | Biosecure

Madhav MalhotraNov 6, 2022, 1:18 AM
11 points
1 comment2 min readEA link

The Fu­ture of Altru­ism is Sus­tain­able Technology

Megan StifelAug 23, 2022, 4:22 AM
3 points
0 comments1 min readEA link

End-To-End En­cryp­tion For EA

Talking TreeAug 30, 2022, 10:10 AM
10 points
7 comments11 min readEA link

AI can ex­ploit safety plans posted on the Internet

Peter S. ParkDec 4, 2022, 12:17 PM
5 points
3 comments1 min readEA link

Tran­si­tion­ing to Sig­nal (Tips & Tricks)

Peter S. ParkJul 23, 2022, 6:57 PM
9 points
7 comments2 min readEA link

My cur­rent im­pres­sions on ca­reer choice for longtermists

Holden KarnofskyJun 4, 2021, 5:07 PM
447 points
37 comments26 min readEA link

Cofound­ing team sought for WordSig.org

Andrew CritchAug 3, 2022, 11:56 PM
16 points
0 comments1 min readEA link

Re­duc­ing long-term risks from malev­olent actors

David_AlthausApr 29, 2020, 8:55 AM
344 points
93 comments37 min readEA link

Tech­nol­ogy is Power: Rais­ing Aware­ness Of Tech­nolog­i­cal Risks

Marc WongFeb 9, 2023, 3:13 PM
3 points
0 comments2 min readEA link

Se­cu­rity Warn­ing: Squares­pace Trans­fer from Google Domains

Wavefront_Security_DaveJun 10, 2024, 9:26 AM
4 points
0 comments3 min readEA link

Trans­for­ma­tive AI and Com­pute—Read­ing List

Frederik BergSep 4, 2023, 6:21 AM
24 points
0 comments1 min readEA link
(docs.google.com)

On ex­clud­ing dan­ger­ous in­for­ma­tion from training

ShayBenMosheNov 17, 2023, 8:09 PM
8 points
0 comments3 min readEA link
(www.lesswrong.com)

Launch­ing Fore­sight In­sti­tute’s AI Grant for Un­der­ex­plored Ap­proaches to AI Safety – Ap­ply for Fund­ing!

elteerkersAug 17, 2023, 7:27 AM
48 points
0 comments2 min readEA link

How can we im­prove In­fo­haz­ard Gover­nance in EA Biose­cu­rity?

Nadia MontazeriAug 5, 2023, 12:03 PM
168 points
27 comments4 min readEA link

Ex­is­ten­tial Cy­ber­se­cu­rity Risks & AI (A Re­search Agenda)

Madhav MalhotraSep 20, 2023, 12:03 PM
7 points
0 comments8 min readEA link

Some gov­er­nance re­search ideas to pre­vent malev­olent con­trol over AGI and why this might mat­ter a hell of a lot

Jim BuhlerMay 23, 2023, 1:07 PM
63 points
5 comments16 min readEA link

Assess­ing the Danger­ous­ness of Malev­olent Ac­tors in AGI Gover­nance: A Pre­limi­nary Exploration

Callum HinchcliffeOct 14, 2023, 9:18 PM
28 points
4 comments9 min readEA link

New refer­ence stan­dard on LLM Ap­pli­ca­tion se­cu­rity started by OWASP

QuantumForestJun 19, 2023, 7:56 PM
5 points
0 comments1 min readEA link

AI-based dis­in­for­ma­tion is prob­a­bly not a ma­jor threat to democracy

Dan WilliamsFeb 24, 2024, 8:01 PM
63 points
8 comments10 min readEA link

On­line in­fosec talk: What even is zero trust?

JarrahJun 8, 2024, 11:54 PM
11 points
0 comments1 min readEA link

Cy­ber­se­cu­rity and AI: The Evolv­ing Se­cu­rity Landscape

Center for AI SafetyMar 14, 2024, 8:14 PM
9 points
0 comments12 min readEA link
(www.safe.ai)

Win­ning Non-Triv­ial Pro­ject: Set­ting a high stan­dard for fron­tier model security

XaviCFJan 8, 2024, 11:20 AM
31 points
0 comments18 min readEA link

Cost-effec­tive­ness of mak­ing a video game with EA concepts

mmKALLLSep 15, 2022, 1:48 PM
8 points
2 comments5 min readEA link

Join the $10K Au­toHack 2024 Tournament

Paul BricmanSep 25, 2024, 11:56 AM
17 points
0 comments1 min readEA link
(noemaresearch.com)

Linux Ker­nel Security

BohemianMiserOct 3, 2024, 12:52 PM
7 points
0 comments1 min readEA link

Soft Na­tion­al­iza­tion: How the US Govern­ment Will Con­trol AI Labs

Deric ChengAug 27, 2024, 3:10 PM
103 points
5 comments21 min readEA link
(www.convergenceanalysis.org)

Dis­in­for­ma­tion as a GCR Threat Mul­ti­plier and Ev­i­dence Based Response

Ari96Jan 24, 2024, 11:19 AM
2 points
0 comments8 min readEA link

Are we drop­ping the ball on Recom­men­da­tion AIs?

Raphaël SOct 23, 2024, 7:37 PM
5 points
0 comments1 min readEA link

Whistle­blow­ing Twit­ter Bot

Mckiev 🔸Dec 26, 2024, 6:18 PM
11 points
1 comment2 min readEA link
(www.lesswrong.com)

AI Lab Re­tal­i­a­tion: A Sur­vival Guide

Jay ReadyJan 4, 2025, 11:05 PM
8 points
1 comment12 min readEA link
(morelightinai.substack.com)

Patch­ing ~All Se­cu­rity-Rele­vant Open-Source Soft­ware?

niplavFeb 25, 2025, 9:35 PM
35 points
3 comments2 min readEA link

The Case for Quan­tum Technologies

Elias X. HuberNov 14, 2024, 1:35 PM
13 points
4 comments6 min readEA link

Elec­tion by Jury: The Ul­ti­mate Demo­cratic Safe­guard in the Age of AI and In­for­ma­tion Warfare

ClayShentrupApr 17, 2025, 7:50 PM
12 points
5 comments27 min readEA link

AI Gover­nance Needs Tech­ni­cal Work

MauSep 5, 2022, 10:25 PM
121 points
3 comments8 min readEA link