-
-
Main Page
-
Threat Scanner
-
Deepfake Image Detector
Inspiration
The idea for CyberGuardAI came from seeing how confusing and risky the internet has become. There are so many scam messages, fake links, and now even AI-generated images that look real. Sometimes it’s hard to tell what’s true and what’s not. I realized that if it’s difficult for me, it must be even harder for others, especially people who are not very familiar with technology. That’s what pushed me to build something that could help.
What it does
CyberGuardAI is a simple tool that helps users stay safe online. It allows users to check suspicious messages or links and tells them whether they are safe or risky. It also has a feature where users can upload images to check if they might be fake or AI-generated. The results are shown clearly with a confidence score and a short explanation so that anyone can understand it easily.
How we built it
I built this project by combining simple logic with basic AI ideas. The system checks patterns in text like common scam words and unusual links. For images, it looks for small irregularities like lighting or unnatural details. The AI runs locally on localhost:11434, so everything is processed on the user’s device. The interface was designed to be clean and beginner-friendly.
Challenges we ran into
One of the biggest challenges was keeping everything simple while still making it useful. Detecting scams and fake images is not always easy, especially without complex models. Another challenge was making the explanations clear so that users can actually understand the results instead of getting confused by technical terms.
Accomplishments that we're proud of
I’m proud that CyberGuardAI is easy to use and solves a real problem. It doesn’t just give results but also explains them in a simple way. Running the AI locally for privacy is also something I focused on, which makes the project more secure and trustworthy.
What we learned
While building this project, I learned more about how online scams and fake content actually work. I also understood how important it is to make technology simple and user-friendly. It was a good experience working on something that has real-world use.
What's next for CyberGuardAI
In the future, I would like to improve the accuracy by using better AI models. I also want to add more features like real-time protection, browser extensions, and maybe a mobile version. The goal is to make CyberGuardAI more powerful while still keeping it simple and easy to use.
Log in or sign up for Devpost to join the conversation.