SDG 4: Quality Education
SDG 9: Industry, Innovation and Infrastructure
2. Project Details
Company or Institution
Human Machine Intelligence In Cybersecurity
General description of the AI solution
Penfield.AI is championing Human-Machine Intelligence in Cybersecurity to address the gap between People, Processes, and Technology in Cybersecurity Operations Centers (SOC). Penfield.AI is the first to model the skill sets of Cybersecurity Analysts and their Processes in real time, enabling real time decision to improve the speed and accuracy of Incident Resolution.
Excellence and Scientific Quality: Please detail the improvements made by the nominee or the nominees’ team or yourself if your applying for the award, and why they have been a success.
Customers, including one of the largest Managed Security Service Provider in Canada, have experienced up to a 38% improvement in Mean Time to Resolve Incidents (MTTR) with Penfield.AI over current state of the art. Penfield is the first to model the skill sets (and state) of Analysts in real time by analyzing Human Computer Interaction data, enabling the application of Reinforcement Learning to perform strategic decisions such as Intelligent Task assignment, Automated Quality Check, Intelligent Context Training and Skill Set Visualization. Penfield has applied for a Full US Patent, a PCT International Patent and another US Provisional Patent drafted by Brion Raffoul LLP.
Scaling of impact to SDGs: Please detail how many citizens/communities and/or researchers/businesses this has had or can have a positive impact on, including particular groups where applicable and to what extent.
Penfield is currently working with several Managed Security Service Providers and a North American Intelligence Organization. Furthermore, Penfield has secured strong Technology Partner Alliances with leading global Cybersecurity companies.
The recent wave of sophisticated cyber-attacks targeting both public and private sectors, with strong emphasis placed on critical infrastructure, has led to nationwide efforts to address the gaps. Aggravating this challenge is the acute shortage of skilled cybersecurity professionals in the industry. Today, nearly half a million public and private cybersecurity jobs remain unfilled in the US alone.
While AI is effective at automating simple repetitive tasks, much of cybersecurity is dynamic and prone to adversarial attacks. Human-Machine Intelligence in cybersecurity can tip the odds that are stacked against us, while simultaneously elevating human potential to address sophisticated attacks.
Scaling of AI solution: Please detail what proof of concept or implementations can you show now in terms of its efficacy and how the solution can be scaled to provide a global impact ad how realistic that scaling is.
Penfield has demonstrated a 38% improvement in Mean Time to Resolve (MTTR) Incidents with a North American Managed Security Service Provider. Other customer deployments are experiencing similar results.
Leveraging Reinforcement Learning enables Penfield to automatically tune our model based on our customers context, enabling a scalable, repeatable model. Penfield improves the speed of attack resolution, while simultaneously upskilling Cyber Analysts on the job by learning from the unique characteristics of the best analysts.
Ethical aspect: Please detail the way the solution addresses any of the main ethical aspects, including trustworthiness, bias, gender issues, etc.
Our design considers ethical aspects of Cybersecurity such as bias, gender issues, trustworthiness, etc. Penfield builds models of skill sets of analysts by learning from their interaction pattern with other cyber tools. This data does not include anything to signify gender, race, educate, etc.
Furthermore, Penfield has demonstrated improvement of Cybersecurity Analyst morale by giving them tasks worthy of their capability, while simultaneously upskilling them to become more impactful in the workforce.