24 citations · 35 across the 5 of their papers we have counts for
3 papers · 1 filter
Scaling Trends in Language Model Robustness
Nikolaus Howe, Ian McKenzie, Oskar Hollinsworth +5
Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt inj…
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…
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…