RiskLens: A Novel Way to Quantify the Risk for Big Data Platform Enhanced by Machine Learning

Big data, characterized by its large volume, diverse formats, and rapid processing speed, possesses remarkable value. However, it is also highly susceptible to security incidents such as data theft, tampering, and destruction during the transmission, storage, and processing stages. Existing methods for assessing security risks in information systems, constrained by human resources and computational methodologies, are not directly applicable to big data platforms. Therefore, researching a quantitative risk assessment scheme tailored to big data platforms, identifying potential risks, and quantitatively analyzing potential losses is a crucial task. To this end, this paper proposes an automated theory for quantitatively assessing risks in big data platforms, integrating traditional quantitative risk assessment methods with the unique features of big data. To validate this theory, a simulation experiment platform was constructed, and the experimental results demonstrate that the proposed scheme can automatically and efficiently quantify risks related to both assets and data processing procedures in big data platforms.