Fighting Cybercrime With Chatbots

The Opportunity

If you experience a cyber crime you want help fast and at any time, day or night.

The Cyber Helpline is a non for profit that provides free support from cyber security experts. They approached us with a complex problem, support in building a chatbot that can navigate the complex world of cyber-crime so they can help victims contain threats and recover.

Fighting Cybercrime With Chatbots

Our Solution

The first thing we needed to understand is how people report and describe these crimes. We wanted to make a system that allowed people to provide as much detail as possible in the most natural way.

Our research showed one thing was very clear. People did not talk in hacking or crime terminology and don’t understand how their personal devices operate at a low level. Most help systems ask you to go to a series of questions to try and slowly self diagnose yourself, but we knew that wasn't effective enough.

Our solution was to allow the user to write freely, letting them explain in their own language what has happened. We then used NLP and Machine Learning to interpret, categorise and diagnose the attack.

Knowledge graphs were used to store possible attack information, we then worked with the cybersecurity expert and used their experience to train the platform over time.

After submitting their issue, the system provided users details on the most likely attack and next steps in protection. If the first diagnosis is not correct the system offers the next most likely cause and learns from this data.

Around 85% of users confirmed that the tool had provided a correct diagnosis. Allowing the cybercrime expert to focus on the cases that need help the most.

If you think you have been a victim of cybercrime try the CyberHelpline here


Around 85% of users confirmed a successful diagnosis with no human interaction needed.

With only 1 in 10 cases reaching its volunteers, it has allowed the helpline to deal with a high volume of cases with minimal cost and resource requirements.


Web chat

The platform uses OpenDialog's web chat module to interact with users

Storing knowledge

We use knowledge graphs to capture the cyber security expert's experience and allow them to train the platform over time

Natural Language Processing

We use the Microsoft Luis stack combined with OpenDialog

Other Projects