A directional source of interference such as jamming can be rejected using a phased array. A common approach to achieve this is to use adaptive beamforming, wherein appropriate weights are selected that form a null at the jammer angles while preserving gain in the target look direction. This paper proposes a novel alternative approach that uses techniques from pattern classification in order to detect a target in the presence of jamming. Simulation results show that the proposed method improves target detection accuracy for situations in which the jammer and target angles are closely spaced. © 2019 IEEE.