The 9/11 events highlight the awareness about the vulnerability of all modes of transportation to terrorist attacks. The marine transportation system, defined as ports and waterways, is the backbone of the world trade and plays a crucial role in homeland security. Because of its strategic importance, a port is extremely vulnerable to terrorist attacks. Providing an effective and efficient port security system has become one of the primary tasks for homeland security. There are various types of terrorist attack threats in a port. In this talk, we focus on scenarios where terrorists use small boats to attack maritime targets (e.g., military vessels, cruise ships, and oil tankers). We consider how to protect these targets by deploying detectors which can sense whether a passing small vessel carries explosive materials. In this talk, we study a defender-attacker Stackelberg game with two players. The leader is the government and the follower is the terrorists. The government first decides the detector deployment strategy to minimize the maximum expected damage cost while keeping the cost of detectors within a budget limit. Detectors are not perfectly reliable and the probability of detection depends on how long a small vessel stays in a detector's effective detection area. The terrorists, after obtaining the full information of detector locations via intelligence, decide the small boat attacking strategy (determine attack routes) with the objective of maximizing the expected damage. A path-based model is established and the resulting problem is formulated as a bi-level nonlinear integer program. An exact algorithm and a heuristic are proposed and testified.