Thread by @interlockweb3

🧠The term Artificial Intelligence is being used as a catch-all for a number of different disciplines but one particular use case may be more important than others: security.

🧐Here's how we use #AI to improve security

🧵👇

First of all, artificial intelligence just means the simulation of human thought by a computer. When you’re using a calculator, you’re already using a computer to “think for you” and do math.

Now you can use a computer to do things like pattern recognition. 🔳🔲🔳🔲🔳🔲

How? The short version is that if you give the computer a step-by-step explanation about how you look at something, you can run it over, and over, and over while correcting its mistakes along the way. 🔁

This is what we call #machinelearning. With enough data and after enough time, the computer eventually becomes really good at finding the right patterns — even better than us. 🔍

There are a ton of ways we’ve been able to use this. One of them is by teaching the computer to classify things with a technique called supervised learning: giving it data that is already labeled and “teaching” it to label new data according to that. 🧑‍🏫

Here’s an example of that:

We can give a computer a #dataset with pictures of fruits along with their corresponding labels (e.g. apple, banana, orange). 🍏🍌🍊

Its task is to match the patterns it sees in each picture to their corresponding label, all on its own.

After many attempts where we evaluate the results and provide feedback, the computer starts to recognize the visual characteristics of each type of fruit. 🧠

The cool thing is that it can be used to classify new, unseen images of fruits.

For instance, when presented with a new image of a strawberry, it will be able to correctly identify it as a strawberry even if that image wasn’t in the dataset it was trained with. 🤯

Now, take this idea and apply it to images of malicious websites. You can train an #AI to successfully detect them while you browse and alert you! 🚨

9/ To get technical: this is possible using an AI algorithm known as a Decision Tree.

You can learn more about the algorithm here: 1.10. Decision Trees — scikit-learn 1.2.1 documentation

That’s exactly what we did with ThreatSlayer. We built a browser extension that keeps you safe with an AI threat detector and trained it on large datasets of known #crypto scams, #phishing links, dangerous URLs, #malware, and more. 💪

What’s even cooler is that we keep training it with more and more data provided by the community. The AI just keeps getting better and better as more people use it. 🌐

But why? Easy. Just like you use your calculator to avoid napkin math every time you split the check at a restaurant, you should be able to use an AI #algorithm to sniff out bad sites. 🕵️

We really think that if we’re improving the web with #decentralization, we should also take it up a notch in terms of security. AI is the right tool for this.

Check out the @interlockweb3 blog to learn more about ThreatSlayer and download it today:

chrome.google.com/webstore/detai…