DECOR: Enhancing Logic Locking Against Machine Learning-Based Attacks

arXiv:2403.01789v1 Announce Type: new
Abstract: Logic locking (LL) has gained attention as a promising intellectual property protection measure for integrated circuits. However, recent attacks, facilitated by machine learning (ML), have shown the potential to predict the correct key in multiple LL schemes by exploiting the correlation of the correct key value with the circuit structure. This paper presents a generic LL enhancement method based on a randomized algorithm that can significantly decrease the correlation between locked circuit netlist and correct …

arxiv attacks attention correlation cs.cr cs.sy eess.sy exploiting intellectual property key key value logic machine machine learning measure predict property protection value