Dr. Aqib Rashid

And it doesn't suffer from high degrees of latency where you're waiting seconds and minutes for a file's verdict to be returned to you.

So all of these kinds of potential challenges we had thought of ahead of time with a view to ensuring that this product will be sustainable going forward.

I think it's the fact that we have managed to solve a very difficult problem.

If you look at academia in general with respect to ML-based or AI-based threat prediction, they paint quite a bleak picture.

where they say that this is a very difficult problem and we don't think this will be necessarily solved because there are so many pitfalls and challenges involved and you might be able to build a model but suddenly it will start drifting and it will have poor performance a month later as you get new types of malware in the wild.

I think though with GlassWall and with Foresight, which is the capability that we've developed and the models that we've developed,

We've shown that not only can you build models that can detect malware or predict malware on day zero, so that is looking at those unknown or zero-day vulnerabilities, but they will do just as well on day one when you know about the vulnerabilities that exist in the wild.

but also months and months down the line, where the threat landscape may have evolved, the types of malware that exist have evolved.

But because we have trained models on deep CDR structural telemetry, what we are somewhat inoculated against is that evolving threat landscape.

So it means that we have proved out that yes, you can build capable models for this problem,

But then equally, you can then deploy these models in an air-gapped environment, in an offline environment, where you have no call to home, you have no internet, and the model will work very well there.

You can deploy this same model in a SaaS solution, maybe in some kind of enterprise network, it will work just as well there.

And all the while proving out along the way that you can do this in a scalable, maintainable way, underpinned by the world-class R&D that we've done here at GlassWall.

So that is the decades of file-based security research that we've done, the AI engineering and AI research that we have conducted.

And of course, the intersection of those two fields has led us to GlassWall Foresight, which of course is undoubtedly the thing I'm most proud of in terms of my work at GlassWall.

I think research and development in general, or science in general rather, is all about making assumptions and making hypotheses about certain problems or certain questions that have come to mind.

And oftentimes they don't stick or they don't land as you'd expect.

For example, an assumption that we made early on in the R&D phase was that certain structural features might be more useful than others for the purposes of trying to detect malware.

But what we quickly saw and quickly found was that where we were looking at certain structural features and certain telemetry, we weren't getting the results that one would expect and one would consider commercially viable.

So that obviously means you then have to go back to the drawing board and think a little deeper about the problem.