Application of Computer Data Mining Technology Based on AKN Algorithm in Denial of Service Attack Defense Detection

Denial of service attacks have become one of the most difficult network security problems because they are easy to implement, difficult to prevent, and difficult to track, and they have brought great harm to the network society. Denial of service (Dos) is a phenomenon in which a large number of useless data packets or obstructive content are maliciously transmitted to the target server, which makes the target server unable to provide users with normal services. Denial of service attack (Dos attack) is a very typical network attack method, and the main harm of Dos attack is to exhaust service resources, making the computer or network unable to provide normal services. And AKN (adaptive Kohonen network) is an adaptive neural network proposed in recent years, and an algorithm summarized by using the characteristics of the neural network is called the AKN algorithm. This algorithm can realize fast, low‐consumption, and high‐precision denial of service detection in complex networks. In the era of big data, network security is becoming more and more important, and in order to maintain the security of network data, this article studies the common forms and principles of Dos attacks, as well as the current corresponding defense detection methods. It also investigates several commonly used algorithms of computer data mining technology, such as clustering algorithms, classification algorithms, neural network algorithms, regression algorithms, website data mining, and association algorithms, and proposes a computer data mining model based on the AKN algorithm. In addition, the computer data mining technology based on the AKN algorithm is used to conduct defensive detection experiments under Dos attacks and compares with classic algorithms. Experimental results show that experiments based on the AKN algorithm have better defensive detection effects than classic algorithms, with a detection accuracy rate of more than 97% and a detection efficiency improvement of more than 20%.