Australian researchers have developed a powerful new technique for discovering hidden “Vault” apps on smartphones. This is a discovery that can help law enforcement with digital research.
This study, conducted by Edith Cowan University and Southern Queensland University, found that Machine Learning (ML) can identify Vault apps with up to 98% accuracy on Android devices.
The Vault app allows users to store files, messages, or other apps behind the layer of encryption. It is often used for privacy, but is increasingly linked to illegal activities such as spying and fraudulent surveillance.
“These apps can mimic normal apps and are extremely difficult to detect,” says Mike Johnstone, Associate Professor at ECU. “Current detection tools rely on prior knowledge of suspicious apps and limit their usefulness.”
In contrast, the new machine learning approach allows you to identify vault apps without the need for existing lists or databases.
Breakthroughs could provide valuable tools to police and security agencies, especially as smartphones become essential to modern life with over 5 billion users worldwide.
“Given how common smartphones are, a non-invasive and accurate way to identify these hidden apps can be a game changer,” Professor Johnston said.
The team is currently planning to expand their research to include more algorithms, wider datasets, and testing non-android devices.
