NIST · ИТ · 7b56fd8ed2428cdea8e4
Baseline Pruning-Based Approach to Trojan Detection in Neural Networks
This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing how NN accuracy responds to systematic pruning. This study leverages the NN models generated for the TrojAI challenges. Our pruning-based approach (1) detects any
NIST · ИТОфициальный источник · 2021-05-07
{
"title_en": "Baseline Pruning-Based Approach to Trojan Detection in Neural Networks",
"designation": "",
"series": "",
"status": "",
"date": "2021-05-07",
"date_original": "May 7, 2021",
"url": "https://www.nist.gov/publications/baseline-pruning-based-approach-trojan-detection-neural-networks",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Michael Majurski",
"abstract_excerpt_en": "This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing how NN accuracy responds to systematic pruning. This study leverages the NN models generated for the TrojAI challenges. Our pruning-based approach (1) detects any",
"id": "7b56fd8ed2428cdea8e4",
"sources": [
"NIST Publications"
],
"source_records": [
{
"title_en": "Baseline Pruning-Based Approach to Trojan Detection in Neural Networks",
"designation": "",
"series": "",
"status": "",
"date": "2021-05-07",
"date_original": "May 7, 2021",
"url": "https://www.nist.gov/publications/baseline-pruning-based-approach-trojan-detection-neural-networks",
"source": "NIST Publications",
"display_en": "",
"authors_en": "Peter Bajcsy , Michael Majurski",
"abstract_excerpt_en": "This paper addresses the problem of detecting trojans in neural networks (NNs) by analyzing how NN accuracy responds to systematic pruning. This study leverages the NN models generated for the TrojAI challenges. Our pruning-based approach (1) detects any"
}
],
"translation_state": "none"
}