AppGNN: Approximation-Aware Functional Reverse Engineering using Graph Neural Networks

TL;DR

This paper introduces AppGNN, a novel approach that enhances the robustness of Graph Neural Networks against Approximate Computing techniques in reverse engineering of circuits, significantly improving classification accuracy in approximate circuit analysis.

Contribution

The paper presents AppGNN, a new platform that enables GNNs to accurately classify and reverse engineer approximate circuits without prior knowledge of the approximation method.

Findings

AxC reduces GNN accuracy from 98% to 53%.

AppGNN improves classification accuracy from 53% to 81% on approximate circuits.

AppGNN effectively counteracts approximation-induced complexity in reverse engineering.

Abstract

The globalization of the Integrated Circuit (IC) market is attracting an ever-growing number of partners, while remarkably lengthening the supply chain. Thereby, security concerns, such as those imposed by functional Reverse Engineering (RE), have become quintessential. RE leads to disclosure of confidential information to competitors, potentially enabling the theft of intellectual property. Traditional functional RE methods analyze a given gate-level netlist through employing pattern matching towards reconstructing the underlying basic blocks, and hence, reverse engineer the circuit's function. In this work, we are the first to demonstrate that applying Approximate Computing (AxC) principles to circuits significantly improves the resiliency against RE. This is attributed to the increased complexity in the underlying pattern-matching process. The resiliency remains effective even for Graph Neural Networks (GNNs) that are presently one of the most powerful state-of-the-art techniques in functional RE. Using AxC, we demonstrate a substantial reduction in GNN average classification accuracy-- from 98% to a mere 53%. To surmount the challenges introduced by AxC in RE, we propose the highly promising AppGNN platform, which enables GNNs (still being trained on exact circuits) to: (i) perform accurate classifications, and (ii) reverse engineer the circuit functionality, notwithstanding the applied approximation technique. AppGNN accomplishes this by implementing a novel graph-based node sampling approach that mimics generic approximation methodologies, requiring zero knowledge of the targeted approximation type. We perform an extensive evaluation and show that, using our method, we can improve the classification accuracy from 53% to 81% when classifying approximate adder circuits that have been generated using evolutionary algorithms, which our method is oblivious of.