Face recognition algorithms are generally vulnerable towards presentation attacks ranging from cost-effective ways such as print and replay to sophisticated mediums such as silicone masks. Carefully designed silicone masks have real-life face texture once wore and can exhibit facial motions; thereby making them challenging to detect. In the literature, while several algorithms have been developed for detecting print and replay based attacks, limited work has been done for detecting silicone mask-based attack. In this research, we propose a computationally efficient solution by utilizing the power of CNN filters, and texture encoding for silicone mask based presentation attacks. The proposed framework operates on the principle of binarizing the image region after convolving the region with the filters learned via CNN operations. On the challenging silicon mask face presentation attack database (SMAD), the proposed feature descriptor shows 3.8% lower error rate than the state-of-the-art algorithms. © 2019 IEEE.