Murat Bilgehan Ertan
PulseAugur coverage of Murat Bilgehan Ertan — every cluster mentioning Murat Bilgehan Ertan across labs, papers, and developer communities, ranked by signal.
-
New formula calibrates DP-SGD noise against membership inference attacks
Researchers have developed a new closed-form formula to calibrate noise levels for DP-SGD, a method used to protect training data by adding noise to gradients. This formula specifically applies to DP-SGD with random all…
-
DP-SGD faces fundamental privacy-utility trade-off limitations
A new research paper published on arXiv details fundamental limitations in Differentially Private Stochastic Gradient Descent (DP-SGD), a common method for private model training. The study, analyzing DP-SGD under the $…
-
New DP-SGD subsampling methods offer improved privacy-utility trade-offs
Two new research papers explore optimized subsampling techniques for Differentially Private Stochastic Gradient Descent (DP-SGD). The first paper, focusing on random shuffling, provides tight upper and lower bounds with…
-
PACZero enables PAC-private fine-tuning of language models with usable utility
Researchers have developed PACZero, a novel method for fine-tuning large language models that offers strong privacy guarantees. This approach utilizes sign quantization of gradients to achieve a privacy regime where mem…