The complexity and outsourcing trend of modern System-on-Chips (SoC) has made Hardware Trojan (HT) a real threat for the SoC security. In the state-of-the-art, many techniques have been proposed in order to detect the HT insertion. Side-channel based methods emerge as a good approach used for the HT detection. They can extract any difference in the power consumption, electromagnetic (EM) emanation, delay propagation, etc. caused by the HT insertion/modification in the genuine design. Therefore, they can be applied to detect the HT even when it is not activated. However, these methods are evaluated on overly simple design prototypes such as AES coprocessors. Moreover, the analytical approach used for these methods is limited by some statistical metrics such as the direct comparison of EM traces or the T-test coefficients. In this paper, we propose two new detection methodologies based on Machine Learning algorithms. The first method consists in applying the supervised Machine Learning (ML) algorithms on raw EM traces for the classification and detection of HT. It offers a detection rate close to 90% and false negative smaller than 5%. For the second method, we propose a method based on the Outlier/Novelty algorithms. This method combined with the T-test based signal processing technique, when compared with state-of-the-art, offers a better performance with a detection rate close to 100% and a false positive smaller than 1%. We have evaluated the performance of our method on a complex target design: RISC-V generic processors. The three HTs with the corresponding sizes of 0.53%, 0.27% and 0.1% of the RISC-V processors are inserted for the experimentation. The experimental results show that the inserted HTs, though minimalist, can be detected using our new methodology.