An optimized deep strategy for recognition and alleviation of DDoS attack in SD-IoT

The attacks like distributed denial-of-service (DDoS) are termed as severe defence issues in data centres, and are considered real network threat. These types of attacks can produce huge disturbances in information technologies. In addition, it is a complex task to determine and fully alleviate DDoS attacks. The new strategy is developed to identify and alleviate DDoS attacks in the Software-Defined Internet of Things (SD-IoT) model. SD-IoT simulation is executed to gather data. The data collected through nodes of SD-IoT are fed to the selection of feature phases. Here, the hybrid process is considered to select features, wherein features, like wrapper-based technique, cosine similarity-based technique, and entropy-based technique are utilized to choose the significant features. Thereafter, the attack discovery process is done with Elephant Water Cycle (EWC)-assisted deep neuro-fuzzy network (DNFN). The EWC is adapted to train DNFN, and here EWC is obtained by grouping Elephant Herd Optimization (EHO) and water cycle algorithm (WCA). Finally, attack mitigation is carried out to secure the SD-IoT. The EWC-assisted DNFN revealed the highest accuracy of 96.9%, TNR of 98%, TPR of 90%, precision of 93%, and F1-score of 91%, when compared with other related techniques.

An Experimental Detection of Distributed Denial of Service Attack in CDX 3 Platform Based on Snort

Distributed Denial of Service (DDoS) attacks pose a significant threat to internet and cloud security. Our study utilizes a Poisson distribution model to efficiently detect DDoS attacks with a computational complexity of O(n). Unlike Machine Learning (ML)-based algorithms, our method only needs to set up one or more Poisson models for legitimate traffic based on the granularity of the time periods during preprocessing, thus eliminating the need for training time. We validate this approach with four virtual machines on the CDX 3.0 platform, each simulating different aspects of DDoS attacks for offensive, monitoring, and defense evaluation purposes. The study further analyzes seven diverse DDoS attack methods. When compared with existing methods, our approach demonstrates superior performance, highlighting its potential effectiveness in real-world DDoS attack detection.

Text information hiding and recovery via wavelet digital watermarking method

According to the wavelet digital watermarking method, wavelet text hiding algorithm is presented for hiding some text information in a signal with white noises and the corresponding recovery algorithm is also presented for obtaining text information from a synthesized signal. Firstly, wavelet text hiding algorithm is introduced and an example is given for demonstrating how to hide text information in a signal s with a white noise ε, where s = f(x) + ε and f(x) is a function such as sin x, cos x and so on. A synthesized signal [Formula: see text] can be obtained by wavelet text hiding algorithm. Then, the corresponding text recovery approach is also introduced and the text information is recovered from the synthesized signal [Formula: see text] by an example. Some figures of the example are shown that the wavelet text hiding algorithm and its recovery are feasible. Moreover, the roles of wavelet function, noise, embedding mode and embedding position are analyzed in the text information hiding and recovering, and it implicates its security. 1000 groups of English texts with different lengths are chosen for illustrating computational complexity and running time of the algorithms. The social application of this approach is explained by a system architecture figure. Finally, some future directions are discussed for our follow-up study.