Blockchain networks serve as a transparent and secure ledger storage solution, yet they remain vulnerable to attacks. There must be some mechanism to protect the blockchain network from attacks. Among various attacks, the Distributed Denial of Service (DDoS) attack is considered severe, which is challenging to detect accurately and reliably. Machine learning techniques are used to detect the attack, which requires exploring all global attack data in a single system, which is difficult in practice. This article proposes a distributed machine learning mechanism called Federated Machine Learning for detecting the presence of DDoS attacks. But in federated machine learning the model itself can be poisoned by the malicious collaborating node which is another problem that this article solves by storing the model in blockchain and by introducing a new reputation-based miner selection procedure. The proposed framework integrates the federation of machine learning within the blockchain network framework for detecting DDoS attacks. Under the integrated framework, miners are used to train the blocks and they also participate in the machine learning training. A dynamic reputation-based miner selection mechanism that can balance exploration and exploitation is proposed for optimal miner selection, which can ensure the high accuracy of the machine learning model and improve the security of blockchain from attacks like DDoS attacks and 51% attacks. The proposed framework is tested with Random Forest, Multilayer Perceptron, and Logistic Regression machine learning algorithms. The proposed mechanism achieved maximum accuracy of 99.1% using random forest model which is superior to the existing mechanism of detection of DDoS attacks.

The substantial rise of information technology has facilitated the methods of access to digital information and internet of things (IOT). Digital image processing handles the digital material to store and distribute more effectively with decreased time and space complexity. However, these tactics undermine the privacy of digital materials. A recent study focuses on shielding digital materials from illicit use and distribution by making reversible data strategies to tackle the risk of privacy breaches for digital content. In this study, a composite reversible data hiding (CRDH) approach is suggested. CRDH employed the integer wavelet transform (HAAR transform) with the HH band’s eigenvalue decomposition. The suggested CRDH first performed the IWT transformation on the cover image (CI) and parsed it into four consecutive frequency subbands, namely, LL, HL, LH, and HH. Sensitive data of the proposed approach are incorporated by merging the HH band of the cover image’s individual values with the encrypted eigenvalues of the confidential data. The choosing of casing art is such a method that values are within a range. The confidential data picture and HH band’s frequency band are roughly the same; thus, modifying the individual values will not affect the quality of the confidential data image and the HH band’s content. The suggested strategy’s primary purpose is to design a data concealing technique that hinders the verification of digital information by maintaining a high rate of peak signal‐to‐noise ratio (PSNR). The PSNR of the existing technology is less than 50 per cent of the total accessible data set. The PSNR value shows the picture’s visual quality, where the PSNR increases the better image quality. Therefore, concealing data is essential for the technique that inhibits authentication and keeps a high rate of PSNR. The suggested approach fulfils this aim, gets a PSNR rate of above 50 per cent, and hits 59 per cent for line.