7 citations · 11 across the 12 of their papers we have counts for
7 papers · 1 filter
Adapting AlphaEvolve to Optimize Fully Homomorphic Encryption on TPUs
Shruthi Gorantala, Jianming Tong, Asra Ali +7
The deployment of Fully Homomorphic Encryption (FHE) at scale is hindered due to its heavy computational overhead. While specialized hardware accelerators like Google Tensor Proces…
Privately Estimating Black-Box Statistics
Günter F. Steinke, Thomas Steinke
Standard techniques for differentially private estimation, such as Laplace or Gaussian noise addition, require guaranteed bounds on the sensitivity of the estimator in question. Bu…
Hush! Protecting Secrets During Model Training: An Indistinguishability Approach
Arun Ganesh, Brendan McMahan, Milad Nasr +2
We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contai…
Near Exact Privacy Amplification for Matrix Mechanisms
Christopher A. Choquette-Choo, Arun Ganesh, Saminul Haque +2
We study the problem of computing the privacy parameters for DP machine learning when using privacy amplification via random batching and noise correlated across rounds via a corre…
The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD
Thomas Steinke, Milad Nasr, Arun Ganesh +7
We propose a simple heuristic privacy analysis of noisy clipped stochastic gradient descent (DP-SGD) in the setting where only the last iterate is released and the intermediate ite…
Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms under Composition
Christian Janos Lebeda, Matthew Regehr, Gautam Kamath +1
We consider the problem of computing tight privacy guarantees for the composition of subsampled differentially private mechanisms. Recent algorithms can numerically compute the pri…
Stealing Part of a Production Language Model
Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham +11
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Speci…