Remarked and recycled counterfeit integratedcircuits (ICs) form a vast majority (≈80-90%) of the totalnumber of counterfeit IC instances. Although different types oftest strategies have been developed for recycled IC detection,techniques that detect remarked ICs are limited. In this paper,we develop a method to detect false remarking of commercialgrade chips into industrial/automotive grade by distinguish-ing power supply rejection ratio (PSRR) of commercial andautomotive grade LDOs from four different vendors. In thisprocess, we use supervised and unsupervised machine learning(ML) methods on PSRR measurements. Our results show abest case accuracy of 90% for both commercial and industrialLDOs with supervised ML. On the other hand, unsupervisedML can detect commercial and industrial LDOs with a best-case accuracy of 75% for both types.