Vietnamese AI detects phishing websites in just 30 seconds with 98% accuracy.

An AI-powered tool for identifying phishing websites, developed by a group of students from Swinburne Vietnam under the guidance of cybersecurity expert Ngo Minh Hieu (Hieu PC, co-founder of the Vietnam Anti-Cyber Fraud Project), has won third prize at the Vietnam Talent Awards. This application is capable of in-depth analysis of website structure and behavior to detect phishing signs in real time, delivering results in under 30 seconds with an accuracy rate of up to 98%.

A tool for identifying phishing websites using artificial intelligence, developed by a team of young authors from the Anti-Fraud Company, won third prize in the category of promising digital technology products.

Fast results in under 30 seconds with up to 98% accuracy.

According to the group's representative, users can easily check the safety of any website simply by pasting the link into the system at https://ai.chongluadao.vn. The application operates entirely online, requires no installation, and only requires entering the suspicious URL. The artificial intelligence system will analyze it in real time and return the results within seconds.

A group of students developed a tool to filter fraudulent websites: https://ai.chongluadao.vn

This tool uses next-generation AI (Large Language Modeling – LLM) to comprehensively assess various elements of a website such as URLs, content, interface, source code, and interaction behavior, thereby providing a risk score on a scale of 10 with detailed explanations, with an accuracy rate of over 98%.

Beyond simply scoring, the system also compiles reports from reputable cybersecurity organizations and displays live video footage of the website interface, allowing users to visually observe the site without physically accessing it, thus avoiding the risk of malware infection.

Notably, this platform is being expanded with a PHP malware scanning feature for WordPress sites at https://wpcheck.chongluadao.vn, helping to detect and prevent malicious code from being injected into the system early on.

Compared to traditional tools that rely solely on blacklists or domain characteristics, this AI solution doesn't simply conclude whether a page is "safe" or "dangerous," but also explains the reasons, provides evidence, and offers multi-source reports, providing the most comprehensive, transparent, and easily understandable perspective for internet users.

One impressive feature is its ability to perform in-depth analysis of website structure and behavior to detect signs of fraud in real time, delivering results in under 30 seconds with an accuracy rate of up to 98%.

"Digital Shield" identifies fake websites.

Cybercrime in Vietnam is escalating at an alarming rate, causing tens of trillions of dong in losses each year. According to the 2024 National Cybersecurity Report, on average, one in every 220 smartphone users is a victim of online fraud, with estimated losses reaching 18,900 billion dong (equivalent to 740 million USD).

In Ho Chi Minh City alone, in the first nine months of 2024, the City Police received 461 cases of online fraud, with the total amount of money stolen estimated at around 982 billion VND.

According to experts, cybercriminals are becoming increasingly sophisticated, constantly changing their methods of fraud from impersonating banks and government agencies to hijacking social media accounts. More worryingly, children and teenagers are becoming the most vulnerable group in the digital age.

This is why the Anti-Fraud team, led by cybersecurity expert Ngo Minh Hieu (Hieu PC), has developed an AI-powered tool for identifying phishing websites, capable of in-depth analysis and detecting signs of fraud in real time.

This is one of the first tools in Vietnam that helps identify phishing websites in real time, completely automatically, using artificial intelligence, integrating a refined big language model and a thinking model.

"The AI tool for identifying phishing websites was developed with the goal of providing a 'digital shield' to help people easily check and identify fake websites early, contributing to protecting the safety of personal information and digital trust of Vietnamese people," the team said.

According to expert Ngo Minh Hieu, the team includes many third-year university students who have taken on key technical roles. The system, developed over four months (from January to April 2025), operates based on a cybersecurity intelligence network, allowing for early scanning and detection of suspicious websites before they harm users.

Immediately after its launch, the tool attracted over 1,000 analyses per day, and in less than four months, that number exceeded 68,000. Each analysis represents a user who received support in protecting their information and assets online.

The tool has also been expanded to include PHP malware scanning for WordPress websites, which has been successfully tested in Vietnix's system with over 100,000 customers. With a simple, user-friendly interface, the ai.chongluadao.vn platform allows anyone, from ordinary users to businesses, to check, analyze, and detect risks in just seconds.

"Positive feedback from users is the biggest motivation for us to continue improving the tool," shared expert Ngo Minh Hieu, adding that the team's goal is to build a safer and more transparent online space for all Vietnamese people.

However, cybersecurity experts advise users to remain vigilant when accessing websites, especially those requesting personal information, bank account details, or OTP codes. While artificial intelligence can assist in highly accurate analysis, awareness of risks and self-protection skills remain the first and most important "shield" against online scams.

Source: https://khoahocdoisong.vn/ai-viet-phat-hien-website-lua-dao-chi-sau-30-giay-chinh-xac-98-post2149064631.html