Robust, static disassembly is an important part of achieving high coverage for many binary code analyses, such as reverse engineering, malware analysis, reference monitor in-lining, and software fault isola- tion. However, one of the major diculties current disassemblers face is dierentiating code from data when they are interleaved. This paper presents a machine learning-based disassembly algorithm that segments an x86 binary into subsequences of bytes and then classies each subse- quence as code or data. The algorithm builds a language model from a set of pre-tagged binaries using a statistical data compression technique. It sequentially scans a new binary executable and sets a breaking point at each potential code-to-code and code-to-data/data-to-code transition. The classication of each segment as code or data is based on the min- imum cross-entropy. Experimental results are presented to demonstrate the eectiveness of the algorithm.