# ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection At Scale

arXiv: https://arxiv.org/abs/2607.23882 · HTML: https://mlsanity.com/paper/2607.23882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 36 references that are in the map.
- First posted on arXiv 26 Jul 2026.

## Builds on (most cited first, 6 of 6)

- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Overcoming Catastrophic Forgetting by Incremental Moment Matching](https://mlsanity.com/paper/1703.08475/) (2017)
- [HW2VEC: A Graph Learning Tool for Automating Hardware Security](https://mlsanity.com/paper/2107.12328/) (2021)
- [Hardware Trojan Detection using Graph Neural Networks](https://mlsanity.com/paper/2204.11431/) (2022)
- [A Golden-Free Formal Method for Trojan Detection in Non-Interfering Accelerators](https://mlsanity.com/paper/2312.06515/) (2023)
- [Automated Hardware Trojan Insertion in Industrial-Scale Designs](https://mlsanity.com/paper/2511.08703/) (2025)

## Abstract (arXiv)

Modern System-on-Chip (SoCs) often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan (HT) detection methods impractical due to their immense scale. The proposed approach incorporates symbolically enabled learning by modeling flattened gate-level netlists as Boolean networks represented as And-Inverter Graphs (AIGs), where all internal nodes are 2-input AND gates and inversions reside on the edges. Each directed connection is expressed as a triple within a Knowledge Graph Embedding (KGE) framework, producing compact, constant-size per-node representations that retain multi-hop structural context. The AIG's bounded fan-in and uniform semantics ensure training and inference complexity scale linearly with edge count, addressing major scalability bottlenecks in HT detection. Symbolically enabled learning across deep datapaths enables the model to differentiate circuit structures from rare and functionally inconsistent connections that signify potential Trojan triggers and payloads. Experiments on large-scale SoC benchmarks demonstrate clear geometric separation between Trojan and benign nodes and practical scalability.