The combination of Deep-learning (DL) and Side-channel analysis (SCA) has been proved in attacking symmetric key cryptography implementations such as AES. This paper aims to show the effectiveness of DL in attacking Post Quantum CRYSTALS-Kyber implementation to find the private key. We propose a CNN model with additional ciphertext knowledge to attack each 12-bit coefficient of the polynomial vector representing the private key. The model labels the trace by value of coefficient for the private key, and so the attacker does not require any knowledge about the implementation, and little or no knowledge about the Kyber algorithm. The model needs only 50 traces to reveal coefficient of the polynomial vector representing the private key.