For better controllability and energy-efficiency, more vehicle functions are being implemented via electronic control systems in place of traditional mechanical control systems. However, such transitions are creating new, unprecedented risks such as software bugs or hardware glitches, all of which can lead to serious safety risks. Recent real-world examples and research literature have been covering them under the name of vehicle misbehavior. In this paper, we present a new way of checking norm operations, called BAD (Brake Anomaly Detection), which detects any vehicle mis-behavior in the Brake-by-Wire system. We focus on the braking system since it is a prototypical safety-critical and cyber-physical system. We first propose a new method for constructing norm models of braking and then show how anomalies are detected by BAD using the constructed models. Finally, we discuss how to verify the results, especially in the context of false positives. Our evaluation results show that BAD can effectively detect various types of anomaly in the braking system.