The vulnerability of facial recognition systems to face morphing attacks is well known. Many different approaches for morphing attack detection (MAD) have been proposed in the scientific literature. However, the MAD algorithms proposed so far have mostly been trained and tested on datasets whose distributions of image characteristics are either very limited (e.g., only created with a single morphing tool) or rather unrealistic (e.g., no print-scan transformation). As a consequence, these methods easily overfit on certain image types and the results presented cannot be expected to apply to real-world scenarios. For example, the results of the latest NIST FRVT MORPH show that the majority of submitted MAD algorithms lacks robustness and performance when considering unseen and challenging datasets. In this work, subsets of the FERET and FRGCv2 face databases are used to create a realistic database for training and testing of MAD algorithms, containing a large number of ICAO-compliant bona fide facial images, corresponding unconstrained probe images, and morphed images created with four different face morphing tools. Furthermore, multiple post-processings are applied on the reference images, e.g., print-scan and JPEG2000 compression. On this database, previously proposed differential morphing algorithms are evaluated and compared. In addition, the application of deep face representations for differential MAD algorithms is investigated. It is shown that algorithms based on deep face representations can achieve very high detection performance (less than 3% D-EER) and robustness with respect to various post-processings. Finally, the limitations of the developed methods are analyzed.