AI ALIGNMENT FORUM
AF

Adversarial Training

This page is a stub.

1

1

Posts tagged Adversarial Training

50Behavioral red-teaming is unlikely to produce clear, strong evidence that models aren't scheming

11mo

1

20Adversarial training, importance sampling, and anti-adversarial training for AI whistleblowing

3y

0

57Takeaways from our robust injury classifier project [Redwood Research]

3y

7

65High-stakes alignment via adversarial training [Redwood Research report]

dmz, LawrenceC, Nate Thomas

3y

15

57Deep Forgetting & Unlearning for Safely-Scoped LLMs

2y

6

39Solving adversarial attacks in computer vision as a baby version of general AI alignment

1y

1

14Adversarial Robustness Could Help Prevent Catastrophic Misuse

2y

15

15Can Generalized Adversarial Testing Enable More Rigorous LLM Safety Evals?

1y

0

10AXRP Episode 17 - Training for Very High Reliability with Daniel Ziegler

3y

0

6Some thoughts on why adversarial training might be useful

4y

4

24Latent Adversarial Training

3y

4

23Beyond the Board: Exploring AI Robustness Through Go

1y

1

15EIS IX: Interpretability and Adversaries

3y

5

14Oversight Leagues: The Training Game as a Feature

3y

0

6EIS XI: Moving Forward

3y

2

Load More (15/18)

Add Posts