The author presents DECOR, a method to enhance logic locking schemes against machine learning attacks by decorrelating the circuit structure from the correct key, significantly reducing key prediction accuracy.
DECOR is a randomized algorithm-based method that significantly decreases the correlation between locked circuit netlist and correct key values, enhancing resilience against ML-based attacks.
DECOR는 머신 러닝 기반 공격에 대한 로직 잠금을 향상시키는 효과적이고 일반적인 구조-키 비상관화 방법을 제시합니다.