# TrojanSAINT: Gate-Level Netlist Sampling-Based Inductive Learning for Hardware Trojan Detection

arXiv: https://arxiv.org/abs/2301.11804 · HTML: https://mlsanity.com/paper/2301.11804/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jan 2023.

## Built on by (most cited first, 9 of 9)

- [AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning](https://mlsanity.com/paper/2402.13946/) (2024)
- [Survey of Graph Neural Network for Internet of Things and NextG Networks](https://mlsanity.com/paper/2405.17309/) (2024)
- [TrojanGYM: A Detector-in-the-Loop LLM for Adaptive RTL Hardware Trojan Insertion](https://mlsanity.com/paper/2601.17178/) (2026)
- [SafeTune: Mitigating Data Poisoning in LLM Fine-Tuning for RTL Code Generation](https://mlsanity.com/paper/2604.27238/) (2026)
- [Automated Hardware Trojan Insertion in Industrial-Scale Designs](https://mlsanity.com/paper/2511.08703/) (2025)
- [TroLLoc: Logic Locking and Layout Hardening for IC Security Closure against Hardware Trojans](https://mlsanity.com/paper/2405.05590/) (2024)
- [Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks](https://mlsanity.com/paper/2606.25589/) (2026)
- [Protocol effects on feature-based hardware-Trojan detection across Trust-Hub families](https://mlsanity.com/paper/2609.07199/) (2026)
- [ReDIL-GNN: Resynthesis Domain Incremental Learning for Circuit Graph Neural Networks](https://mlsanity.com/paper/2609.18595/) (2026)

## Abstract (arXiv)

We propose TrojanSAINT, a graph neural network (GNN)-based hardware Trojan (HT) detection scheme working at the gate level. Unlike prior GNN-based art, TrojanSAINT enables both pre-/post-silicon HT detection. TrojanSAINT leverages a sampling-based GNN framework to detect and also localize HTs. For practical validation, TrojanSAINT achieves on average (oa) 78% true positive rate (TPR) and 85% true negative rate (TNR), respectively, on various TrustHub HT benchmarks. For best-case validation, TrojanSAINT even achieves 98% TPR and 96% TNR oa. TrojanSAINT outperforms related prior works and baseline classifiers. We release our source codes and result artifacts.