Providing support For Cybercrime Victims
with CyberHelpLine and OpenDialog
85%
confirmed correct diagnosis
- 80%
direct call volume
English
Language
BAckground
If you experience a cybercrime you want help fast and at any time, day or night.
The Cyber Helpline is a non-profit that provides free support from cybersecurity 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. It needed to be free and available 24/7 to support the victims of cybercrime because expert help is expensive and in short supply.
With Cybercrime attacks being hard to describe even for experienced users, The Cyber Helpline needed an automated service that would provide effective assistance through simple conversations and graceful handover to experts where it fails to reliably identify the attack.
the Solution
The solution allows the user to write freely, letting them explain in their own language what has happened. OpenDialog’s reasoning engine then uses NLP and Machine Learning services to undertake syntax & entity analysis to assist with the interpretation, categorisation and diagnosis of the attack.
After submitting their issue, the system provides the user with details on the most likely attack and next steps in protection. If the first diagnosis is not correct, the system then offers the next most likely cause and learns from this data.
Knowledge graphs are used to store possible attack information which are then shared with the user based on the analyse of the attack. Cybersecurity experts at the Cyber Helpline use their experience to train the platform, both improving responses to already handled threats and adding capabilities for unhandled threats which are raised.
The platform uses OpenDialog’s Webchat module to interact with users. This custom Webchat client allows users to enter information as long-form text describing the cyber attack issue they are facing. This means users do not have to go through a long list of questions.
The solution in action
impact
- 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.