Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Hasegawa, Marcello"'
In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independently, in other cases, it occurs
Externí odkaz:
http://arxiv.org/abs/2106.11384
Machine learned models trained on organizational communication data, such as emails in an enterprise, carry unique risks of breaching confidentiality, even if the model is intended only for internal use. This work shows how confidentiality is distinc
Externí odkaz:
http://arxiv.org/abs/2105.13418
Autor:
Mireshghallah, Fatemehsadat, Inan, Huseyin A., Hasegawa, Marcello, Rühle, Victor, Berg-Kirkpatrick, Taylor, Sim, Robert
Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a popular choice t
Externí odkaz:
http://arxiv.org/abs/2103.07567
Autor:
Mukherjee, Sudipto, Mukherjee, Subhabrata, Hasegawa, Marcello, Awadallah, Ahmed Hassan, White, Ryen
Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks. In this work, we explore a new application, Smart-To-Do, that helps users wit
Externí odkaz:
http://arxiv.org/abs/2005.06282