Denial of Service (DoS) attacks aim at rendering a computer or network incapable of providing normal services by exploiting bugs or holes of system programs or network communication protocols. Existing DoS attack defense mechanisms (e.g., firewalls, intrusion detection systems, intrusion prevention systems) typically rely on data gathered from gateways of network systems. Because these data are IP-layer or above packet information, existing defense mechanisms are incapable of detecting internal attacks or attackers who disguise themselves by spoofing the source IP addresses of their packets. To address the aforementioned limitations of existing DoS attack defense mechanisms, we propose a classification-based DoS attack detection technique on the basis of the SNMP MIB II data from the network interface to induce a DoS detection model from a set of training examples that consist of both normal and attack traffic data). The constructed DoS detection model is then used for predicting whether a network traffic from the network interface is a DoS attack. To empirically evaluate our proposed classification-based DoS attack detection technique, we collect, with various traffic aggregation intervals (including 1, 3, and 5 minutes), normal network traffic data from two different environments (including an enterprise network, and a university campus network) and attack network traffics (including TCP SYN Flood, Land, Fake Ping, and Angry Ping) from an independent experimental network. Our empirical evaluation results show that the detection accuracy of the proposed technique reaches 98.59% or above in the two network environments. The evaluation results also suggest that the proposed technique is insensitive to the traffic aggregation intervals examined and has a high distinguishing power for the four types of DoS attacks under investigation.