OBJECTIVE : The automatic detection of epileptic seizures in EEG data from extended recordings can make an important contribution to the diagnosis of epilepsy as it can efficiently reduce the workload of medical staff. METHODS : This paper describes how features based on cross-bispectrum can help with the detection of epileptic seizure activity in EEG data. Features were extracted from multi-channel intracranial EEG (iEEG) data from the Freiburg iEEG recordings of 21 patients with focal epilepsy. These features were used as a support vector machine classifier input to discriminate ictal from inter-ictal states. A post-processing method was applied to the classifier output in order to improve classification accuracy. RESULTS : A sensitivity of 95.8%, specificity of 96.7%, and accuracy of 96.8% were achieved. The false detection rate (FDR) was zero for 10 patients and very low for the rest. CONCLUSIONS : The results show that the proposed method distinguishes better between ictal and inter-ictal iEEG epochs than other seizure detection methods. The proposed method has a higher accuracy index than achievable with a number of previously described approaches. Also, the method is rapid and easy and may be helpful in online epileptic seizure detection and prediction systems.