4 papers
Expert Selections In MoE Models Reveal (Almost) As Much As Text
Amir Nuriyev, Gabriel Kulp
We present a text-reconstruction attack on mixture-of-experts (MoE) language models that recovers tokens from expert selections alone. In MoE models, each token is routed to a subs…
Verifying International Agreements on AI: Six Layers of Verification for Rules on Large-Scale AI Development and Deployment
Mauricio Baker, Gabriel Kulp, Oliver Marks +2
The risks of frontier AI may require international cooperation, which in turn may require verification: checking that all parties follow agreed-on rules. For instance, states might…
Hardware-Enabled Mechanisms for Verifying Responsible AI Development
Aidan O'Gara, Gabriel Kulp, Will Hodgkins +7
Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also…
Swift: High-Performance Sparse Tensor Contraction for Scientific Applications
Andrew Ensinger, Gabriel Kulp, Victor Agostinelli +2
In scientific fields such as quantum computing, physics, chemistry, and machine learning, high dimensional data are typically represented using sparse tensors. Tensor contraction i…