RESUMO
In today's digital landscape, securing multimedia visual information-specifically color images-is of critical importance across a range of sectors, including the burgeoning fields of logistics and supply chain management. Traditional Visual Cryptography (VC) schemes lay the groundwork for encrypting visual data by fragmenting a secret image into multiple shares, thereby ensuring no single share divulges the secret. Nevertheless, VC faces challenges in ascertaining the integrity of reconstructed images, especially when shares are manipulated maliciously. Existing solutions often necessitate additional shares or a trusted third party for integrity verification, thereby adding complexity and potential security risks. This paper introduces a novel Cheating-Resistant Visual Cryptographic Protocol (CRVC) for Color Images that aims to address these limitations. Utilizing self-computational models, this enhanced protocol simplifies the integrated integrity verification process, eliminating the need for extra shares. A standout feature is its capability to securely transmit meaningful shares for color images without compromising the quality of the reconstructed image as the PSNR maintains to be ∞. Experimental findings substantiate the protocol's resilience against quality degradation and its effectiveness in verifying the authenticity of the reconstructed image. This innovative approach holds promise for a wide array of applications, notably in sectors requiring secure document transmission, such as Logistics and Supply Chain Management, E-Governance, Medical and Military Applications.
RESUMO
In today's digital era, many applications generate massive data streams that must be sequenced and processed immediately. Therefore, storing large amounts of data for analysis is impractical. Now, this infinite amount of evolving data confronts concept drifts in data stream classification. Concept drift is a phenomenon in which the distribution of input data or the relationship between input data and target label changes over time. If the drifts are not addressed, the learning model's performance suffers. Non-stationary data streams must be processed as they arrive, and neural networks' built-in capabilities aid in the processing of huge non-stationary data streams. We proposed an adaptive windowing approach based on a gated recurrent unit, a variant of the recurrent neural network incrementally trained on incoming data (for the real-world airline and synthetic Streaming Ensemble Algorithm (SEA) datasets), and employed elastic weight consolidation with the Fisher information matrix to prevent forgetting. Unlike the traditional fixed window methodology, the proposed model dynamically increases the window size if the prediction is correct and reduces it if drifts occur. As a result, an adaptive recurrent neural network model can adapt to changes in the non-stationary data stream and provide consistent performance. Moreover, the findings revealed that on the airline and the SEA dataset, the proposed model outperforms state-of-the-art methods by achieving 67.74% and 91.70% accuracy, respectively. Further, the results demonstrated that the proposed model has a better accuracy of 3.6% and 1.6% for the SEA and the airline dataset, respectively.
