RSS

Com­puter Se­cu­rity & Cryptography

Tag

Se­cu­rity Mind­set and Or­di­nary Paranoia

Eliezer Yudkowsky25 Nov 2017 17:53 UTC
132 points
25 comments29 min readLW link

On De­stroy­ing the World

Chris_Leong28 Sep 2020 7:38 UTC
82 points
86 comments5 min readLW link

Bet­ter Pass­word Peppering

Yoav Ravid24 Aug 2021 10:19 UTC
6 points
9 comments3 min readLW link

Work on Se­cu­rity In­stead of Friendli­ness?

Wei Dai21 Jul 2012 18:28 UTC
71 points
107 comments2 min readLW link

En­tropy isn’t suffi­cient to mea­sure pass­word strength

benwr17 Jan 2022 6:41 UTC
36 points
30 comments2 min readLW link
(www.benwr.net)

POC || GTFO cul­ture as par­tial an­ti­dote to al­ign­ment wordcelism

lc15 Mar 2023 10:21 UTC
146 points
11 comments7 min readLW link

AI Safety is Drop­ping the Ball on Clown Attacks

trevor22 Oct 2023 20:09 UTC
69 points
77 comments34 min readLW link

The dan­ger of er­ror descriptions

gistya25 Mar 2021 20:05 UTC
−1 points
2 comments3 min readLW link

Ho­mo­mor­phic en­cryp­tion and Bitcoin

jimrandomh19 May 2011 1:07 UTC
10 points
9 comments1 min readLW link

What is Cryp­to­graph­i­cally Possible

paulfchristiano24 Dec 2010 4:58 UTC
27 points
19 comments5 min readLW link

Cryp­to­graphic Boxes for Un­friendly AI

paulfchristiano18 Dec 2010 8:28 UTC
71 points
162 comments5 min readLW link

Paper re­view: A Cryp­to­graphic Solu­tion to a Game The­o­retic Problem

victorsintnicolaas24 Apr 2021 11:54 UTC
23 points
4 comments6 min readLW link

Crypt­anal­y­sis as Episte­mol­ogy? (pag­ing cryp­ton­erds)

SilasBarta6 Apr 2011 19:06 UTC
17 points
42 comments1 min readLW link

[Question] How good is se­cu­rity for LessWrong and the Align­ment Fo­rum?

Quintin Pope4 Oct 2021 22:27 UTC
20 points
4 comments1 min readLW link

Se­cure homes for digi­tal people

paulfchristiano10 Oct 2021 15:50 UTC
161 points
37 comments9 min readLW link1 review
(sideways-view.com)

gamers be­ware: mod­ded Minecraft has new malware

the gears to ascension7 Jun 2023 13:49 UTC
14 points
5 comments1 min readLW link
(github.com)

Up­skil­ling, bridge-build­ing, re­search on se­cu­rity/​cryp­tog­ra­phy and AI safety

Allison Duettmann20 Apr 2023 22:32 UTC
14 points
0 comments4 min readLW link

[Question] Is there a con­ve­nient way to make “sealed” pre­dic­tions?

Daniel Kokotajlo6 May 2022 23:00 UTC
32 points
20 comments1 min readLW link

The Un­bear­able Light­ness of Web Vulnerabilities

aiiixiii29 May 2022 21:13 UTC
29 points
2 comments1 min readLW link
(www.theoreticalstructures.io)

[Question] How much does cy­ber­se­cu­rity re­duce AI risk?

Darmani12 Jun 2022 22:13 UTC
34 points
23 comments1 min readLW link

Crypto-fed Computation

aaguirre13 Jun 2022 21:20 UTC
24 points
7 comments7 min readLW link

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

elspood21 Jun 2022 23:55 UTC
361 points
42 comments7 min readLW link1 review

Ac­cess to pow­er­ful AI might make com­puter se­cu­rity rad­i­cally easier

Buck8 Jun 2024 6:00 UTC
97 points
14 comments6 min readLW link

Uniker­nels: No Longer an Aca­demic Exercise

Martin Sustrik23 Oct 2018 11:40 UTC
27 points
1 comment3 min readLW link
(250bpm.com)

5 Rea­sons Why Govern­ments/​Mili­taries Already Want AI for In­for­ma­tion Warfare

trevor30 Oct 2023 16:30 UTC
32 points
0 comments10 min readLW link

[Question] What is good Cy­ber Se­cu­rity Ad­vice?

Gunnar_Zarncke24 Oct 2022 23:27 UTC
30 points
12 comments2 min readLW link

[Question] In soft­ware en­g­ineer­ing, what are the up­per limits of Lan­guage-Based Se­cu­rity?

mako yass27 Dec 2020 5:50 UTC
13 points
6 comments1 min readLW link

Hacker-AI – Does it already ex­ist?

Erland Wittkotter7 Nov 2022 14:01 UTC
3 points
13 comments11 min readLW link

n of m ring signatures

DanielFilan4 Dec 2023 20:00 UTC
50 points
7 comments1 min readLW link
(danielfilan.com)

11 dice­ware words is enough

15 Feb 2024 0:13 UTC
23 points
6 comments1 min readLW link
(threadreaderapp.com)

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

Akash7 Apr 2023 15:47 UTC
34 points
1 comment4 min readLW link

Not Get­ting Hacked

jefftk21 Dec 2022 21:40 UTC
40 points
14 comments7 min readLW link
(www.jefftk.com)

Pri­vacy Tradeoffs

jefftk29 Dec 2022 3:40 UTC
13 points
1 comment2 min readLW link
(www.jefftk.com)

How Likely is Los­ing a Google Ac­count?

jefftk30 Jan 2023 0:20 UTC
52 points
11 comments3 min readLW link
(www.jefftk.com)

Free­dom and Pri­vacy of Thought Architectures

JohnBuridan20 Jul 2024 21:43 UTC
5 points
2 comments1 min readLW link

AI Gover­nance & Strat­egy: Pri­ori­ties, tal­ent gaps, & opportunities

Akash3 Mar 2023 18:09 UTC
56 points
2 comments4 min readLW link

[Question] Hoard­ing Gmail-ac­counts in a post-CAPTCHA world?

Alexander Gietelink Oldenziel11 Mar 2023 16:08 UTC
7 points
3 comments1 min readLW link

AI se­cu­rity might be helpful for AI alignment

Igor Ivanov6 Jan 2023 20:16 UTC
35 points
1 comment2 min readLW link

Prevent­ing model exfil­tra­tion with up­load limits

ryan_greenblatt6 Feb 2024 16:29 UTC
66 points
21 comments14 min readLW link

Fron­tier Model Security

Vaniver26 Jul 2023 4:48 UTC
32 points
1 comment3 min readLW link
(www.anthropic.com)

AXRP Epi­sode 30 - AI Se­cu­rity with Jeffrey Ladish

DanielFilan1 May 2024 2:50 UTC
25 points
0 comments79 min readLW link

The rise of AI in cybercrime

BobyResearcher30 Jul 2023 20:19 UTC
−15 points
1 comment2 min readLW link
(riseofAIincybercryme)

Biose­cu­rity Cul­ture, Com­puter Se­cu­rity Culture

jefftk30 Aug 2023 16:40 UTC
103 points
10 comments2 min readLW link
(www.jefftk.com)

Hacker-AI and Digi­tal Ghosts – Pre-AGI

Erland Wittkotter19 Oct 2022 15:33 UTC
9 points
7 comments8 min readLW link

Deep­fake(?) Phishing

jefftk21 Oct 2022 14:30 UTC
37 points
9 comments1 min readLW link
(www.jefftk.com)

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

Peter S. Park3 Nov 2022 16:02 UTC
4 points
4 comments11 min readLW link

Safe Devel­op­ment of Hacker-AI Coun­ter­mea­sures – What if we are too late?

Erland Wittkotter1 Dec 2022 7:59 UTC
3 points
0 comments14 min readLW link

Non-Tech­ni­cal Prepa­ra­tion for Hacker-AI and Cy­ber­war 2.0+

Erland Wittkotter19 Dec 2022 11:42 UTC
2 points
0 comments25 min readLW link

Hacker-AI and Cy­ber­war 2.0+

Erland Wittkotter19 Dec 2022 11:46 UTC
2 points
0 comments15 min readLW link

The 2/​3 rule for multi-fac­tor authentication

RomanHauksson4 Feb 2023 2:57 UTC
4 points
0 comments1 min readLW link
(roman.computer)

Fix­ing In­sider Threats in the AI Sup­ply Chain

Madhav Malhotra7 Oct 2023 13:19 UTC
20 points
2 comments5 min readLW link

Nav­i­gat­ing the Attackspace

Jonas Kgomo12 Dec 2023 13:59 UTC
1 point
0 comments2 min readLW link

Plan­ning to build a cryp­to­graphic box with perfect secrecy

Lysandre Terrisse31 Dec 2023 9:31 UTC
40 points
6 comments11 min readLW link

Agent mem­branes and causal distance

Chipmonk2 Jan 2024 22:43 UTC
20 points
3 comments3 min readLW link

Disprov­ing and par­tially fix­ing a fully ho­mo­mor­phic en­cryp­tion scheme with perfect secrecy

Lysandre Terrisse26 May 2024 14:56 UTC
16 points
1 comment18 min readLW link

Pro­tect­ing agent boundaries

Chipmonk25 Jan 2024 4:13 UTC
11 points
6 comments2 min readLW link

In­cor­po­rat­ing Mechanism De­sign Into De­ci­sion Theory

StrivingForLegibility26 Jan 2024 18:25 UTC
17 points
4 comments4 min readLW link

How im­por­tant is AI hack­ing as LLMs ad­vance?

Artyom Karpov29 Jan 2024 18:41 UTC
1 point
0 comments6 min readLW link

End-to-end hack­ing with lan­guage models

tchauvin5 Apr 2024 15:06 UTC
29 points
0 comments8 min readLW link

Can Large Lan­guage Models effec­tively iden­tify cy­ber­se­cu­rity risks?

emile delcourt30 Aug 2024 20:20 UTC
18 points
0 comments11 min readLW link

Cy­ber­se­cu­rity of Fron­tier AI Models: A Reg­u­la­tory Review

25 Apr 2024 14:51 UTC
8 points
0 comments8 min readLW link

How to Fake Decryption

ohmurphy5 Sep 2024 9:18 UTC
12 points
0 comments4 min readLW link
(ohmurphy.substack.com)

Can star­tups be im­pact­ful in AI safety?

13 Sep 2024 19:00 UTC
12 points
0 comments6 min readLW link

Con­sider at­tend­ing the AI Se­cu­rity Fo­rum ’24, a 1-day pre-DEFCON event

Charlie Rogers-Smith12 Jul 2024 23:01 UTC
21 points
0 comments1 min readLW link

Se­cret Col­lu­sion: Will We Know When to Un­plug AI?

16 Sep 2024 16:07 UTC
55 points
7 comments31 min readLW link

Us­ing an LLM per­plex­ity filter to de­tect weight exfiltration

Adam Karvonen21 Jul 2024 18:18 UTC
25 points
11 comments2 min readLW link

The Prag­matic Side of Cryp­to­graph­i­cally Box­ing AI

Bart Jaworski6 Aug 2024 17:46 UTC
6 points
0 comments9 min readLW link

Join the $10K Au­toHack 2024 Tournament

Paul Bricman25 Sep 2024 11:54 UTC
5 points
0 comments1 min readLW link
(noemaresearch.com)

GPT-4o Guardrails Gone: Data Poi­son­ing & Jailbreak-Tuning

1 Nov 2024 0:10 UTC
17 points
0 comments6 min readLW link
(far.ai)

AI in­fosec: first strikes, zero-day mar­kets, hard­ware sup­ply chains, adop­tion barriers

Allison Duettmann1 Apr 2023 16:44 UTC
41 points
0 comments9 min readLW link

Boundaries-based se­cu­rity and AI safety approaches

Allison Duettmann12 Apr 2023 12:36 UTC
43 points
2 comments6 min readLW link

The Virus—Short Story

Michael Soareverix13 Apr 2023 18:18 UTC
4 points
0 comments4 min readLW link

Cryp­to­graphic and aux­iliary ap­proaches rele­vant for AI safety

Allison Duettmann18 Apr 2023 14:18 UTC
7 points
0 comments6 min readLW link

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

Madhav Malhotra23 Apr 2023 17:37 UTC
15 points
0 comments11 min readLW link
(forum.effectivealtruism.org)

[Question] How much should e-sig­na­tures have to cost a coun­try?

FlorianH21 Nov 2023 22:45 UTC
5 points
5 comments1 min readLW link

[Question] AI in­ter­pretabil­ity could be harm­ful?

Roman Leventov10 May 2023 20:43 UTC
13 points
2 comments1 min readLW link

Us­ing GPT-Eliezer against ChatGPT Jailbreaking

6 Dec 2022 19:54 UTC
170 points
85 comments9 min readLW link

Microsoft and Google us­ing LLMs for Cybersecurity

Phosphorous18 May 2023 17:42 UTC
6 points
0 comments5 min readLW link

Trans­former Ar­chi­tec­ture Choice for Re­sist­ing Prompt In­jec­tion and Jail-Break­ing Attacks

RogerDearnaley21 May 2023 8:29 UTC
9 points
1 comment4 min readLW link

Scry­ing for out­comes where the prob­lem of deep­fakes has been solved

mako yass15 Apr 2019 4:45 UTC
26 points
10 comments4 min readLW link

Es­ti­mat­ing the con­se­quences of de­vice de­tec­tion tech

Jsevillamol8 Jul 2018 18:25 UTC
27 points
4 comments7 min readLW link

On See­ing Through ‘On See­ing Through: A Unified The­ory’: A Unified Theory

gwern15 Jun 2019 18:57 UTC
26 points
0 comments1 min readLW link
(www.gwern.net)

Com­puter se­cu­rity story

Perplexed17 Feb 2011 0:26 UTC
5 points
30 comments1 min readLW link

Se­cu­rity Mind­set and the Lo­gis­tic Suc­cess Curve

Eliezer Yudkowsky26 Nov 2017 15:58 UTC
104 points
49 comments20 min readLW link

Op­ti­mal User-End In­ter­net Se­cu­rity (Or, Ra­tional In­ter­net Brows­ing)

Arkanj3l9 Sep 2011 18:23 UTC
2 points
23 comments1 min readLW link

Proof of pos­te­ri­or­ity: a defense against AI-gen­er­ated misinformation

jchan17 Jul 2023 12:04 UTC
33 points
3 comments5 min readLW link

Pri­vacy in a Digi­tal World

Faustify27 Jul 2023 10:46 UTC
2 points
0 comments5 min readLW link

Neu­ral pro­gram syn­the­sis is a dan­ger­ous technology

syllogism12 Jan 2018 16:19 UTC
10 points
6 comments2 min readLW link

Re­vis­it­ing the Man­i­fold Hypothesis

Aidan Rocke1 Oct 2023 23:55 UTC
13 points
19 comments4 min readLW link

Ap­ply to the Con­cep­tual Boundaries Work­shop for AI Safety

Chipmonk27 Nov 2023 21:04 UTC
50 points
0 comments3 min readLW link

Lat­a­cora might be of in­ter­est to some AI Safety organizations

NunoSempere25 Nov 2021 23:57 UTC
14 points
10 comments1 min readLW link
(www.latacora.com)

[Question] Trans­fer­ring cre­dence with­out trans­fer­ring ev­i­dence?

Kaarel4 Feb 2022 8:11 UTC
11 points
6 comments3 min readLW link

Im­proved Se­cu­rity to Prevent Hacker-AI and Digi­tal Ghosts

Erland Wittkotter21 Oct 2022 10:11 UTC
4 points
3 comments12 min readLW link
No comments.