LESSWRONG
Wikitags
LW

Adversarial Examples (AI)

Multicore, Ruby

Adversarial Examples (AI)

Written by Multicore, Ruby last updated 14th Dec 2024

This page is a stub.

Posts tagged Adversarial Examples (AI)

8

681SolidGoldMagikarp (plus, prompt generation)

Jessica Rumbelow, mwatkins

2y

206

3

157Ironing Out the Squiggles

11mo

36

3

70AI Safety in a World of Vulnerable Machine Learning Systems

AdamGleave, EuanMcLean

2y

28

2

124There are (probably) no superhuman Go AIs: strong human players beat the strongest AIs

2y

34

2

124Deep Forgetting & Unlearning for Safely-Scoped LLMs

1y

30

2

87Solving adversarial attacks in computer vision as a baby version of general AI alignment

7mo

8

2

59Human beats SOTA Go AI by learning an adversarial policy

2y

32

2

38What progress have we made on automated auditing?

9mo

1

2

35If I were a well-intentioned AI... I: Image classifier

Stuart_Armstrong

5y

4

2

31Adversarial Policies Beat Professional-Level Go AIs

2y

35

2

30Adversarial Robustness Could Help Prevent Catastrophic Misuse

1y

18

2

13The Goodhart Game

5y

5

2

12AXRP Episode 1 - Adversarial Policies with Adam Gleave

4y

5

2

5RAIN: Your Language Models Can Align Themselves without Finetuning - Microsoft Research 2023 - Reduces the adversarial prompt attack success rate from 94% to 19%!

Singularian2501

1y

0

1

142High-stakes alignment via adversarial training [Redwood Research report]

dmz, LawrenceC, Nate Thomas

3y

29