Optical fibres are the backbone of modern Information Technology infrastructure connecting billions of users through high-speed networks. With a drastic increase in the number of internet users, vulnerability and security issues in the optical fibre network become increasingly important. In this paper, we propose a detection method for early warning of anomalies in optical networks. The method is based on monitoring and analyzing changes in the state of polarization of the optical signal targeting differentiating between different physical impacts and movements of the fibre caused by e.g. eavesdropping, cut by digging and thunderstorms.