Zobrazeno 1 - 10
of 20 851
pro vyhledávání: '"A. Fanti"'
Automated marker makers (AMMs) are a class of decentralized exchanges that enable the automated trading of digital assets. They accept deposits of digital tokens from liquidity providers (LPs); tokens can be used by traders to execute trades, which g
Externí odkaz:
http://arxiv.org/abs/2411.10399
Information disclosure can compromise privacy when revealed information is correlated with private information. We consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian adversary can g
Externí odkaz:
http://arxiv.org/abs/2410.17095
Autor:
Lee, Sangyun, Xu, Yilun, Geffner, Tomas, Fanti, Giulia, Kreis, Karsten, Vahdat, Arash, Nie, Weili
Consistency models have recently been introduced to accelerate sampling from diffusion models by directly predicting the solution (i.e., data) of the probability flow ODE (PF ODE) from initial noise. However, the training of consistency models requir
Externí odkaz:
http://arxiv.org/abs/2410.14895
As an information-flow privacy property, opacity characterizes whether a malicious external observer (referred to as an intruder) is able to infer the secret behavior of a system. This paper addresses the problem of opacity enforcement using edit fun
Externí odkaz:
http://arxiv.org/abs/2410.08471
Data valuation is a class of techniques for quantitatively assessing the value of data for applications like pricing in data marketplaces. Existing data valuation methods define a value for a discrete dataset. However, in many use cases, users are in
Externí odkaz:
http://arxiv.org/abs/2410.04386
Publikováno v:
Twentieth Symposium on Usable Privacy and Security (SOUPS 2024), pp. 159-177. 2024
In the international development community, the term "digital public goods" is used to describe open-source digital products (e.g., software, datasets) that aim to address the United Nations (UN) Sustainable Development Goals. DPGs are increasingly b
Externí odkaz:
http://arxiv.org/abs/2406.15842
Autor:
Hou, Charlie, Shrivastava, Akshat, Zhan, Hongyuan, Conway, Rylan, Le, Trang, Sagar, Adithya, Fanti, Giulia, Lazar, Daniel
On-device training is currently the most common approach for training machine learning (ML) models on private, distributed user data. Despite this, on-device training has several drawbacks: (1) most user devices are too small to train large models on
Externí odkaz:
http://arxiv.org/abs/2406.02958
Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows, which iterati
Externí odkaz:
http://arxiv.org/abs/2405.20320
Almost Instance-optimal Clipping for Summation Problems in the Shuffle Model of Differential Privacy
Differentially private mechanisms achieving worst-case optimal error bounds (e.g., the classical Laplace mechanism) are well-studied in the literature. However, when typical data are far from the worst case, \emph{instance-specific} error bounds -- w
Externí odkaz:
http://arxiv.org/abs/2403.10116
Differentially private (DP) machine learning pipelines typically involve a two-phase process: non-private pre-training on a public dataset, followed by fine-tuning on private data using DP optimization techniques. In the DP setting, it has been obser
Externí odkaz:
http://arxiv.org/abs/2402.18905