核心概念
DECOR는 머신 러닝 기반 공격에 대한 로직 잠금을 향상시키는 효과적이고 일반적인 구조-키 비상관화 방법을 제시합니다.
統計
"Numerical results show that the proposed method can efficiently degrade the accuracy of state-of-the-art ML-based attacks down to around 50%, resulting in negligible advantage versus random guessing."
"The average KPA across all the benchmark circuits is 87.89%, with the KPA of c6288 being as high as 97.22%."
"By applying DECOR, the average KPA drops significantly to 52.70% and 50.43%, when N = 8 and N = 16, respectively."
引用
"Logic locking (LL) has gained attention as a promising intellectual property protection measure for integrated circuits."
"DECOR is an enhancement method that can increase the resilience of any LL scheme to ML-based attacks."