NIST · ИТ · 2949e0033e5b52575d44
Trojan Detection Evaluation: Finding Hidden Behavior in AI Models
Neural Networks are trained on data, learn relationships in that data, and then are deployed to the world to operate on new data. For example, a traffic sign classification AI can differentiate stop signs and speed limit signs. One potential problem is
NIST · ИТОфициальный источник · 2020-10-10
{
"title_en": "Trojan Detection Evaluation: Finding Hidden Behavior in AI Models",
"designation": "",
"series": "",
"status": "",
"date": "2020-10-10",
"date_original": "October 10, 2020",
"url": "https://www.nist.gov/publications/trojan-detection-evaluation-finding-hidden-behavior-ai-models",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael Majurski , Derek Juba , Timothy Blattner , Peter Bajcsy , Walid Keyrouz",
"abstract_excerpt_en": "Neural Networks are trained on data, learn relationships in that data, and then are deployed to the world to operate on new data. For example, a traffic sign classification AI can differentiate stop signs and speed limit signs. One potential problem is",
"id": "2949e0033e5b52575d44",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Trojan Detection Evaluation: Finding Hidden Behavior in AI Models",
"designation": "",
"series": "",
"status": "",
"date": "2020-10-10",
"date_original": "October 10, 2020",
"url": "https://www.nist.gov/publications/trojan-detection-evaluation-finding-hidden-behavior-ai-models",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Michael Majurski , Derek Juba , Timothy Blattner , Peter Bajcsy , Walid Keyrouz",
"abstract_excerpt_en": "Neural Networks are trained on data, learn relationships in that data, and then are deployed to the world to operate on new data. For example, a traffic sign classification AI can differentiate stop signs and speed limit signs. One potential problem is"
}
],
"translation_state": "none"
}