Firewalls are a key element in network security. They are in charge of filtering the traffic of the network in compliance with a number of access-control rules that enforce a given security policy. In an always-evolving context, where security policies must often be updated to respond to new security requirements, knowing with precision the policy being enforced by a network system is a critical information. Otherwise, we risk to hamper the proper evolution of the system and compromise its security. Unfortunately, discovering such enforced policy is an error-prone and time consuming task that requires low-level and, often, vendor-specific expertise since firewalls may be configured using different languages and conform to a complex network topology. To tackle this problem, we propose a model-driven reverse engineering approach able to extract the security policy implemented by a set of firewalls in a working network, easing the understanding, analysis and evolution of network security policies.