Talks·20 min
Guilherme Santos
Surveys how attackers poison, invert and evade machine learning models, from prompt injection to adversarial patches.
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
Talks·20 min
Guilherme Santos
Surveys how attackers poison, invert and evade machine learning models, from prompt injection to adversarial patches.