Counterfeit money refers to fake or imitation currency that is produced with the idea to deceive. The advancement of color printing technology has increased the rate of fake currency note printing and duplicating the notes on a very large scale. A few years back, printing could be done in a print house, but now anyone can print a currency note with maximum accuracy using a simple laser printer. As a result, the issue of fake notes instead of genuine ones has increased very largely. Ethiopia has been unfortu nately cursed with the problems like corruption and black money. And counterfeit currency notes are also a big problem to it. Some researchers are conduct with this problem in Ethiopia. However, there is no reliable recognition system to identify forged banknotes rather than using security features by UV and detector pen. In order to solve the problem, we develop a model that detects fake currency notes in less time and in a more efficient manner by using a large dataset to record better accuracy and processing time of detection of counterfeit money. The dataset are collected from different bank and police office. Resizing, color conversion, augmentation and normalization preprocessing techniques are applied with python environment. The proposed model (EBDM) efficiently detects counterfeit Ethiopian paper currency notes by adapting a multi-layered Deep Convolutional Neural Network. Model experimented by front side, backside and all sides of the banknote with RGB and grayscale image. Experimental analysis has been demonstrated with different models of CNN such as InceptionV3, MobileNetV2, and VGG net. The model is tested using genuine Ethiopian currencies and counterfeit Ethiopian currencies that achieved 95.84% training accuracy and 89.99% test accuracy. This work is vital for automation in many sectors such as vending machines, railway ticket counters, banking systems, shopping malls, currency exchange services, etc. Keyword: Ethiopian currency, counterfeit detection, image preprocessing, convolutional neural network