Day 1 Stream 2·49 min
Itsik Mantin
Shows how poisoned training data skews machine learning models and how threshold-based learning can limit the damage.
aimachine-learningattack+2
DEF CON 34 talks are here: 354 talks, summarized and searchable.
Browse DEF CON 341 talk in the archive.
1–1 of 1 talk
Day 1 Stream 2·49 min
Itsik Mantin
Shows how poisoned training data skews machine learning models and how threshold-based learning can limit the damage.