Complementary security systems are widely deployed in networks to protect digital assets. Alert correlation is essential to understanding the security threats and taking appropriate actions. This paper proposes a novel correlation approach based on triggering events and common resources. One of the key concepts in our approach is triggering events, whicha re the (low-level) events that trigger alerts. By grouping alerts that share "similar" triggering events, a set of alerts can be partitioned into different clusters such that the alerts in the same cluster may correspond to the same attack. Our approach further examines whether the alerts in each cluster are consistent with relevant network and host configurations, which help analysts to partially identify the severity of alerts and clusters. The other key concept in our approach is input and output resources. Intuitively, input resources are the necessary resources for an attack to succeed, and output resources are the resources that an attack supplies if successful. This paper proposes to model each attack through sopecifying input and output resources. By identifying the "common" resources between output resources of one attack and input resources of another, it discovers causal relationships between alert clusters and builds attack scenarios. The experimental results demonstrate the usefulness of the proposed techniques.