Garbage In, Garbage Out: How Purportedly Great Machine Learning Models can be Screwed Up by Bad Data

Дата: 08.01.2020. Автор: CISO CLUB. Категории: Подкасты и видео по информационной безопасности

In this presentation, I will present sensitivity results from the same deep learning model designed to detect malicious URLs, trained and tested across 3 different sources of URL data. After reviewing the results, we’ll dive into what caused our results by looking into: 1) surface differences between the different sources of data, and 2) higher level feature activations that our neural net identified in certain data sets, but failed to identify in others.

By Hillary Sanders

Full Abstract & Presentation Materials: https://www.blackhat.com/us-17/briefings.html#garbage-in-garbage-out-how-purportedly-great-machine-learning-models-can-be-screwed-up-by-bad-data

CISO CLUB

Об авторе CISO CLUB

Редакция портала cisoclub.ru. Добавляйте ваш материал на сайт в разделе "Разместить публикацию".
Читать все записи автора CISO CLUB

Добавить комментарий

Ваш адрес email не будет опубликован. Обязательные поля помечены *