Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time.
Via Bruce Schneier.
A personal website by Khürt Williams, with inchoate ramblings on technology, photography, beer, and geekery.
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time.
Via Bruce Schneier.