Codes that aim to detect any error regardless of its multiplicity are referred to as security oriented codes. Most of these codes are designed to protect uniformly distributed codewords; there are few solutions which are used in protecting systems with non-uniformly distributed words. The paper introduces a new encoding method, termed “Level-Out encoding”, for cases in which some words are more likely to appear than others and compares the effectiveness of the different methods. The advantage of the suggested coding scheme is demonstrated by simulations with two different types of attackers - a Blind Attacker, limited to the knowledge of the a priori information word and codeword distribution, and a Memory Based Attacker with access to the conditional probabilities based on previous information words as well.