NIST · ИТ · 7fb72eb85c594ffbe7cd
Interactive Simulations of Backdoors in Neural Networks
This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable
NIST · ИТОфициальный источник · 2024-05-21
{
"title_en": "Interactive Simulations of Backdoors in Neural Networks",
"designation": "",
"series": "",
"status": "",
"date": "2024-05-21",
"date_original": "May 21, 2024",
"url": "https://www.nist.gov/publications/interactive-simulations-backdoors-neural-networks",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Maxime Bros , Matthew Coudron",
"abstract_excerpt_en": "This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable",
"id": "7fb72eb85c594ffbe7cd",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Interactive Simulations of Backdoors in Neural Networks",
"designation": "",
"series": "",
"status": "",
"date": "2024-05-21",
"date_original": "May 21, 2024",
"url": "https://www.nist.gov/publications/interactive-simulations-backdoors-neural-networks",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Maxime Bros , Matthew Coudron",
"abstract_excerpt_en": "This work addresses the problem of planting and defending cryptographic-based backdoors in artificial intelligence models. The motivation comes from our lack of understanding and the implications of using cryptographic techniques for planting undetectable"
}
],
"translation_state": "none"
}