The digital radio frequency memory (DRFM) repeat jammer, which can transmit signals of close signature to real target returns, is a typical low-cost electronic attacker and poses threats to radar systems. One can optimize multiple-input multiple-output (MIMO) radar waveforms to magnify the difference between deceptive signals and real targets, and in this paper, we examine the performance improvement achieved by designing classification algorithms. The training samples are theoretical target returns and theoretical constant-modulus deceptive signals, both modulated with different Doppler frequencies. Three classifiers, namely the support vector machines (SVM), Naive Bayes and k-Nearest Neighbor (kNN), are considered and the SVM performs the best. With 128-chips phase-coded transmit signals, the waveform optimization algorithm achieves a 6dB signal-to-noise ratio (SNR) improvement at the 90% classification rate.