all InfoSec news
AI Model Disgorgement: Methods and Choices. (arXiv:2304.03545v1 [cs.LG])
cs.CR updates on arXiv.org arxiv.org
Responsible use of data is an indispensable part of any machine learning (ML)
implementation. ML developers must carefully collect and curate their datasets,
and document their provenance. They must also make sure to respect intellectual
property rights, preserve individual privacy, and use data in an ethical way.
Over the past few years, ML models have significantly increased in size and
complexity. These models require a very large amount of data and compute
capacity to train, to the extent that any …
ai model collect complexity compute data datasets developers document intellectual property large machine machine learning ml models privacy provenance respect responsible rights size train training