The tools under development include a browser add-on with corresponding back-end software that tracks users’ online activities for incidents of aggression and distress. Once operational, this will be supported by a ‘software stack’ that analyses social web data to detect and alert users of fraudulent activity, and another add-on that detects when a user is about to share sensitive content (e.g. photos or contact details) with potentially risky recipients. An instant warning will be issued to the user/guardian. A further add-on will include controls and authentication lists for web surfers, such as watermarking, cryptography or steganography – hiding messages or information within other text, data, and files. All browser add-ons and the back-end social web data analytics tools will be user tested in a series of pilots before being released to the public. Key work will be carried out by experienced and early-stage researchers under the EU-funded Marie Skłodowska-Curie research and innovation staff exchange programme. The project’s academic partners will contribute know-how on user experience, large-scale data processing, machine-learning, data-mining, and content confidentiality techniques. Meanwhile, industrial partners will provide expertise in production-grade software development and access to real-world online social network data and end-users.