5 citations · 9 across the 7 of their papers we have counts for
8 papers
Step-resolved data attribution for looped transformers
Georgios Kaissis, David Mildenberger, Juan Felipe Gomez +2
We study how individual training examples shape the internal computation of looped transformers, where a shared block is applied for recurrent iterations to enable latent reaso…
Optimal conversion from Rényi Differential Privacy to -Differential Privacy
Anneliese Riess, Juan Felipe Gomez, Flavio du Pin Calmon +2
We prove the conjecture stated in Appendix F.3 of \citet{zhu2022optimalaccountingdifferentialprivacy}: among all conversion rules that map a Rényi Differential Privacy (RDP) profil…
Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy
Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis +4
Differentially private (DP) mechanisms are difficult to interpret and calibrate because existing methods for mapping standard privacy parameters to concrete privacy risks -- re-ide…
Optimizing Noise Distributions for Differential Privacy
Atefeh Gilani, Juan Felipe Gomez, Shahab Asoodeh +3
We propose a unified optimization framework for designing continuous and discrete noise distributions that ensure differential privacy (DP) by minimizing Rényi DP, a variant of DP,…
Gaussian DP for Reporting Differential Privacy Guarantees in Machine Learning
Juan Felipe Gomez, Bogdan Kulynych, Georgios Kaissis +4
Current practices for reporting differential privacy (DP) guarantees for machine learning (ML) algorithms such as DP-SGD provide an incomplete and potentially misleading picture. F…
AI-Machine Learning-Enabled Tokamak Digital Twin
William Tang, Eliot Feibush, Ge Dong +9
In addressing the Department of Energy's April, 2022 announcement of a Bold Decadal Vision for delivering a Fusion Pilot Plant by 2035, associated software tools need to be develop…
Attack-Aware Noise Calibration for Differential Privacy
Bogdan Kulynych, Juan Felipe Gomez, Georgios Kaissis +2
Differential privacy (DP) is a widely used approach for mitigating privacy risks when training machine learning models on sensitive data. DP mechanisms add noise during training to…
Algorithmic Arbitrariness in Content Moderation
Juan Felipe Gomez, Caio Vieira Machado, Lucas Monteiro Paes +1
Machine learning (ML) is widely used to moderate online content. Despite its scalability relative to human moderation, the use of ML introduces unique challenges to content moderat…