Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Schuster, Roei"'
Retrieval-augmented generation (RAG) systems respond to queries by retrieving relevant documents from a knowledge database, then generating an answer by applying an LLM to the retrieved documents. We demonstrate that RAG systems that operate on datab
Externí odkaz:
http://arxiv.org/abs/2406.05870
Publikováno v:
Computational Linguistics, Vol 46, Iss 2, Pp 499-510 (2020)
Recent developments in neural language models (LMs) have raised concerns about their potential misuse for automatically spreading misinformation. In light of these concerns, several studies have proposed to detect machine-generated fake news by captu
Externí odkaz:
https://doaj.org/article/15e331f3e56845f5ba03d596c9e46bb4
Autor:
Biton, Dudi, Misra, Aditi, Levy, Efrat, Kotak, Jaidip, Bitton, Ron, Schuster, Roei, Papernot, Nicolas, Elovici, Yuval, Nassi, Ben
Machine learning (ML) models are known to be vulnerable to a number of attacks that target the integrity of their predictions or the privacy of their training data. To carry out these attacks, a black-box adversary must typically possess the ability
Externí odkaz:
http://arxiv.org/abs/2309.02159
Autor:
Boenisch, Franziska, Dziedzic, Adam, Schuster, Roei, Shamsabadi, Ali Shahin, Shumailov, Ilia, Papernot, Nicolas
Federated learning (FL) is a framework for users to jointly train a machine learning model. FL is promoted as a privacy-enhancing technology (PET) that provides data minimization: data never "leaves" personal devices and users share only model update
Externí odkaz:
http://arxiv.org/abs/2301.04017
A learned system uses machine learning (ML) internally to improve performance. We can expect such systems to be vulnerable to some adversarial-ML attacks. Often, the learned component is shared between mutually-distrusting users or processes, much li
Externí odkaz:
http://arxiv.org/abs/2212.10318
To produce accurate predictions, language models (LMs) must balance between generalization and memorization. Yet, little is known about the mechanism by which transformer LMs employ their memorization capacity. When does a model decide to output a me
Externí odkaz:
http://arxiv.org/abs/2210.03588
When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE, computes output labels by aggregating the predictions of a (possibly d
Externí odkaz:
http://arxiv.org/abs/2209.10732
Autor:
Boenisch, Franziska, Dziedzic, Adam, Schuster, Roei, Shamsabadi, Ali Shahin, Shumailov, Ilia, Papernot, Nicolas
In federated learning (FL), data does not leave personal devices when they are jointly training a machine learning model. Instead, these devices share gradients, parameters, or other model updates, with a central party (e.g., a company) coordinating
Externí odkaz:
http://arxiv.org/abs/2112.02918
Feed-forward layers constitute two-thirds of a transformer model's parameters, yet their role in the network remains under-explored. We show that feed-forward layers in transformer-based language models operate as key-value memories, where each key c
Externí odkaz:
http://arxiv.org/abs/2012.14913
Code autocompletion is an integral feature of modern code editors and IDEs. The latest generation of autocompleters uses neural language models, trained on public open-source code repositories, to suggest likely (not just statically feasible) complet
Externí odkaz:
http://arxiv.org/abs/2007.02220