Adversarial Examples

Tag

SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow and mwatkins

5 Feb 2023 22:02 UTC

651 points

199 comments12 min readLW link

AI Safety in a World of Vulnerable Machine Learning Systems

AdamGleave and EuanMcLean

8 Mar 2023 2:40 UTC

58 points

10 comments29 min readLW link

(far.ai)

AXRP Episode 1 - Adversarial Policies with Adam Gleave

DanielFilan29 Dec 2020 20:41 UTC

12 points

5 comments33 min readLW link

The Goodhart Game

John_Maxwell18 Nov 2019 23:22 UTC

13 points

5 comments5 min readLW link

If I were a well-intentioned AI… I: Image classifier

Stuart_Armstrong26 Feb 2020 12:39 UTC

35 points

4 comments5 min readLW link

Adversarial Policies Beat Professional-Level Go AIs

sanxiyn3 Nov 2022 13:27 UTC

31 points

35 comments1 min readLW link

(goattack.alignmentfund.org)

Human beats SOTA Go AI by learning an adversarial policy

Vanessa Kosoy19 Feb 2023 9:38 UTC

55 points

32 comments1 min readLW link

(goattack.far.ai)

[AN #62] Are adversarial examples caused by real but imperceptible features?

Rohin Shah22 Aug 2019 17:10 UTC

27 points

10 comments9 min readLW link

(mailchi.mp)

The Achilles Heel Hypothesis for AI

scasper13 Oct 2020 14:35 UTC

20 points

6 comments1 min readLW link

SmartyHeaderCode: anomalous tokens for GPT3.5 and GPT-4

AdamYedidia15 Apr 2023 22:35 UTC

70 points

18 comments6 min readLW link

A Search for More ChatGPT / GPT-3.5 / GPT-4 “Unspeakable” Glitch Tokens

Martin Fell9 May 2023 14:36 UTC

14 points

6 comments6 min readLW link

EIS IX: Interpretability and Adversaries

scasper20 Feb 2023 18:25 UTC

29 points

5 comments8 min readLW link

EIS X: Continual Learning, Modularity, Compression, and Biological Brains

scasper21 Feb 2023 16:59 UTC

14 points

3 comments3 min readLW link

EIS XII: Summary

scasper23 Feb 2023 17:45 UTC

12 points

0 comments6 min readLW link

Evidence Sets: Towards Inductive-Biases based Analysis of Prosaic AGI

bayesian_kitten16 Dec 2021 22:41 UTC

22 points

10 comments21 min readLW link

High-stakes alignment via adversarial training [Redwood Research report]

dmz, LawrenceC and Nate Thomas

5 May 2022 0:59 UTC

142 points

29 comments9 min readLW link

Adversarial attacks and optimal control

Jan22 May 2022 18:22 UTC

17 points

7 comments8 min readLW link

(universalprior.substack.com)

No comments.