Abstract Models trained for classifification often assume that all testing classes are known while training. As a result, when presented with an unknown class during testing, such closed-set assumption forces the model to classify it as one of the known classes. However, in a real world scenario, classifification models are likely to encounter such examples. Hence, identifying those examples as unknown becomes critical to model performance. A potential solution to overcome this problem lies in a class of learning problems known as open-set recognition. It refers to the problem of identifying the unknown classes during testing, while maintaining performance on the known classes. In this paper, we propose an open-set recognition algorithm using class conditioned auto-encoders with novel training and testing methodologies. In this method, training procedure is divided in two sub-tasks, 1. closed-set classifification and, 2. open-set identifification (i.e. identifying a class as known or unknown). Encoder learns the fifirst task following the closed-set classifification training pipeline, whereas decoder learns the second task by reconstructing conditioned on class identity. Furthermore, we model reconstruction errors using the Extreme Value Theory of statistical modeling to fifind the threshold for identifying known/unknown class samples. Experiments performed on multiple image classi- fification datasets show that the proposed method performs signifificantly better than the state of the art methods. The source code is available at: github.com/otkupjnoz/c2ae.