Fighting cybercrime with chatbots for the Cyber Helpline

Cybercrime doesn’t discriminate, it affects businesses and private individuals alike, and is a rising threat, both in the UK and globally.

The Cyber Helpline is a not-for-profit which facilitates the provision of free support by cyber security experts to UK cybercrime victims. The organisation partnered with Manifesto to deliver this support via a chatbot.

24/7 help

The Cyber Helpline recognised a need to support victims of cybercrime at any time of day or night. Particularly during a pandemic, where human support in call centres had been compromised, and rates of cybercrime were rising.

The charity sought the expertise of Manifesto to design and build a chatbot which could navigate the complex world of cybercrime. The technology had to be able to aid victims, by both containing threats where possible, and offering comprehensive support in the post-crime, recovery phase.

Speaking clearly

User research indicated that individual victims of cybercrime do not use technical terminology when describing what has happened to them.

To better provide access to help, our team had to allow the user to write freely, using their own natural language to explain what has happened to them, rather than asking you a series of questions to diagnose the problem. This led us to Natural Language Processing (NLP) and Machine Learning technology, which could interpret, categories and diagnose an attack without requiring technical terms.

Our teams used knowledge graphs, which can connect intent, phrases, nouns and adjectives to associated concepts. This way, we could capture the cyber security experts’ experience, whilst building the platform in a way which meant it could continue to be trained by them over time, as new instances of cybercrime evolve.

85% correct diagnosis rate

The Cyber Helpline’s new chatbot uses OpenDialog’s web chat module to interact with cybercrime victims. It allows them to report their problem descriptively, and provides them with detail on the most likely cause of their attack. And, importantly, gives the next steps to protect them.

If the first diagnosis is not correct, the chatbot suggests the next most likely cause, and learns from this data. So far, it’s provided around 85% of users with a correct diagnosis. Only 1 in 10 cases now reach volunteers, which allows cybercrime experts to focus on more complex, high-risk cases that demand the most help and attention.

If you’re concerned you have been a victim of cybercrime, you can access The Cyber Helpline here.