10 citations · 11 across the 3 of their papers we have counts for
3 papers · 1 filter
Can Go AIs be adversarially robust?
Tom Tseng, Euan McLean, Kellin Pelrine +2
Prior work found that superhuman Go AIs can be defeated by simple adversarial strategies, especially "cyclic" attacks. In this paper, we study whether adding natural countermeasure…
Cliff-Learning
Tony T. Wang, Igor Zablotchi, Nir Shavit +1
We study the data-scaling of transfer learning from foundation models in the low-downstream-data regime. We observe an intriguing phenomenon which we call cliff-learning. Cliff-lea…
Adversarial Policies Beat Superhuman Go AIs
Tony T. Wang, Adam Gleave, Tom Tseng +8
We attack the state-of-the-art Go-playing AI system KataGo by training adversarial policies against it, achieving a >97% win rate against KataGo running at superhuman settings. Our…