GNNUnlock: Graph Neural Networks-based Oracle-less Unlocking Scheme for Provably Secure Logic Locking

Lilas Alrahis1,a, Satwik Patnaik2,a, Faiq Khalid3, Muhammad Abdullah Hanif3, Hani Saleh1, Muhammad Shafique4,a and Ozgur Sinanoglu4,b
1Department of Electrical Engineering and Computer Science, Khalifa University, Abu Dhabi, UAE
alilas.alrahis@ku.ac.ae
2Electrical & Computer Engineering, Texas A&M University, College Station, Texas, USA
asatwik.patnaik@tamu.edu
3Institute of Computer Engineering, Technische Universität Wien, Vienna, Austria
4Division of Engineering, New York University Abu Dhabi, UAE
amuhammad.shafique@nyu.edu
bozgursin@nyu.edu

ABSTRACT


Logic locking is a holistic design-for-trust technique that aims to protect the design intellectual property (IP) from untrustworthy entities throughout the supply chain. Functional and structural analysis-based attacks successfully circumvent state-ofthe- art, provably secure logic locking (PSLL) techniques. However, such attacks are not holistic and target specific implementations of PSLL. Automating the detection and subsequent removal of protection logic added by PSLL while accounting for all possible variations is an open research problem.
In this paper, we propose GNNUnlock, the first-of-its-kind oracle-less machine learning-based attack on PSLL that can identify any desired protection logic without focusing on a specific syntactic topology. The key is to leverage a well-trained graph neural network (GNN) to identify all the gates in a given locked netlist that belong to the targeted protection logic, without requiring an oracle. This approach fits perfectly with the targeted problem since a circuit is a graph with an inherent structure and the protection logic is a sub-graph of nodes (gates) with specific and common characteristics. GNNs are powerful in capturing the nodes’ neighborhood properties, facilitating the detection of the protection logic. To rectify any misclassifications induced by the GNN, we additionally propose a connectivity analysis-based post-processing algorithm to successfully remove the predicted protection logic, thereby retrieving the original design.

Keywords: Logic Locking, IP Protection, Graph Neural Networks, Machine Learning, Oracle-Less Attack.



Full Text (PDF)