NIST · ИТ · 81af573bc2f75b409319
Explaining poisoned AI models
This work presents a hierarchical approach to explaining poisoned artificial intelligence (AI) models. The motivation comes from using AI models in security and safety-critical applications, for instance, AI models for classifying road traffic signs in
NIST · ИТОфициальный источник · 2025-06-11
{
"title_en": "Explaining poisoned AI models",
"designation": "",
"series": "",
"status": "",
"date": "2025-06-11",
"date_original": "June 11, 2025",
"url": "https://www.nist.gov/publications/explaining-poisoned-ai-models",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Antonio Cardone , Philippe Dessauw , Chenyi Ling , Michael Majurski , Timothy Blattner , Derek Juba , Walid Keyrouz",
"abstract_excerpt_en": "This work presents a hierarchical approach to explaining poisoned artificial intelligence (AI) models. The motivation comes from using AI models in security and safety-critical applications, for instance, AI models for classifying road traffic signs in",
"id": "81af573bc2f75b409319",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Explaining poisoned AI models",
"designation": "",
"series": "",
"status": "",
"date": "2025-06-11",
"date_original": "June 11, 2025",
"url": "https://www.nist.gov/publications/explaining-poisoned-ai-models",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Antonio Cardone , Philippe Dessauw , Chenyi Ling , Michael Majurski , Timothy Blattner , Derek Juba , Walid Keyrouz",
"abstract_excerpt_en": "This work presents a hierarchical approach to explaining poisoned artificial intelligence (AI) models. The motivation comes from using AI models in security and safety-critical applications, for instance, AI models for classifying road traffic signs in"
}
],
"translation_state": "none"
}