Zobrazeno 1 - 10
of 1 759
pro vyhledávání: '"Badih, A."'
Autor:
Ghazi, Badih, Harrison, Charlie, Hosabettu, Arpana, Kamath, Pritish, Knop, Alexander, Kumar, Ravi, Leeman, Ethan, Manurangsi, Pasin, Sahu, Vikas
The Privacy Sandbox initiative from Google includes APIs for enabling privacy-preserving advertising functionalities as part of the effort around limiting third-party cookies. In particular, the Private Aggregation API (PAA) and the Attribution Repor
Externí odkaz:
http://arxiv.org/abs/2412.16916
Autor:
Chua, Lynn, Ghazi, Badih, Harrison, Charlie, Leeman, Ethan, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sinha, Amer, Zhang, Chiyuan
We introduce the Balls-and-Bins sampling for differentially private (DP) optimization methods such as DP-SGD. While it has been common practice to use some form of shuffling in DP-SGD implementations, privacy accounting algorithms have typically assu
Externí odkaz:
http://arxiv.org/abs/2412.16802
Autor:
Chua, Lynn, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Sinha, Amer, Zhang, Chiyuan
We provide new lower bounds on the privacy guarantee of the multi-epoch Adaptive Batch Linear Queries (ABLQ) mechanism with shuffled batch sampling, demonstrating substantial gaps when compared to Poisson subsampling; prior analysis was limited to a
Externí odkaz:
http://arxiv.org/abs/2411.04205
Autor:
Xie, Chulin, Huang, Yangsibo, Zhang, Chiyuan, Yu, Da, Chen, Xinyun, Lin, Bill Yuchen, Li, Bo, Ghazi, Badih, Kumar, Ravi
Large language models (LLMs) achieve good performance on challenging reasoning benchmarks, yet could also make basic reasoning mistakes. This contrasting behavior is puzzling when it comes to understanding the mechanisms behind LLMs' reasoning capabi
Externí odkaz:
http://arxiv.org/abs/2410.23123
We study differential privacy (DP) in a multi-party setting where each party only trusts a (known) subset of the other parties with its data. Specifically, given a trust graph where vertices correspond to parties and neighbors are mutually trusting,
Externí odkaz:
http://arxiv.org/abs/2410.12045
Autor:
Huang, Yangsibo, Liu, Daogao, Chua, Lynn, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Manurangsi, Pasin, Nasr, Milad, Sinha, Amer, Zhang, Chiyuan
Machine unlearning algorithms, designed for selective removal of training data from models, have emerged as a promising approach to growing privacy concerns. In this work, we expose a critical yet underexplored vulnerability in the deployment of unle
Externí odkaz:
http://arxiv.org/abs/2410.09591
Autor:
Berke, Alex, Bacis, Enrico, Ghazi, Badih, Kamath, Pritish, Kumar, Ravi, Lassonde, Robin, Manurangsi, Pasin, Syed, Umar
Browser fingerprinting can be used to identify and track users across the Web, even without cookies, by collecting attributes from users' devices to create unique "fingerprints". This technique and resulting privacy risks have been studied for over a
Externí odkaz:
http://arxiv.org/abs/2410.06954
Autor:
Bey, Sara, Fields, Shelby S., Combs, Nicholas G., Márkus, Bence G., Beke, Dávid, Wang, Jiashu, Ievlev, Anton V., Zhukovskyi, Maksym, Orlova, Tatyana, Forró, László, Bennett, Steven P., Liu, Xinyu, Assaf, Badih A.
The discovery of an anomalous Hall effect (AHE) sensitive to the magnetic state of antiferromagnets can trigger a new era of spintronics, if materials that host a tunable and strong AHE are identified. Altermagnets are a new class of materials that c
Externí odkaz:
http://arxiv.org/abs/2409.04567
We study the differentially private (DP) empirical risk minimization (ERM) problem under the semi-sensitive DP setting where only some features are sensitive. This generalizes the Label DP setting where only the label is sensitive. We give improved u
Externí odkaz:
http://arxiv.org/abs/2406.19040
We study the problem of computing pairwise statistics, i.e., ones of the form $\binom{n}{2}^{-1} \sum_{i \ne j} f(x_i, x_j)$, where $x_i$ denotes the input to the $i$th user, with differential privacy (DP) in the local model. This formulation capture
Externí odkaz:
http://arxiv.org/abs/2406.16305