LESSWRONG
Wikitags
LW

1

Adversarial Training

1

This page is a stub.

Posts tagged Adversarial Training

2

157Ironing Out the Squiggles

11mo

36

2

143Takeaways from our robust injury classifier project [Redwood Research]

3y

12

2

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

dmz, LawrenceC, Nate Thomas

3y

29

2

124Deep Forgetting & Unlearning for Safely-Scoped LLMs

1y

30

2

100Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming

5mo

4

2

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

7mo

8

2

40Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing

3y

0

2

30Adversarial Robustness Could Help Prevent Catastrophic Misuse

1y

18

2

25Can Generalized Adversarial Testing Enable More Rigorous LLM Safety Evals?

8mo

0

2

17AI Safety 101 - Chapter 5.2 - Unrestricted Adversarial Training

Charbel-Raphaël

1y

0

2

16AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler

3y

0

2

9Some thoughts on why adversarial training might be useful

3y

6

1

52Latent Adversarial Training

3y

13

1

41Beyond the Board: Exploring AI Robustness Through Go

9mo

2

1

30EIS IX: Interpretability and Adversaries

2y

8