Ranking Apps on Privacy

The last thing you want to do when installing a new, free app on your phone is to scroll through pages of information on what kind of access to your personal information it requires. App builders count on this, and their intrusive apps harvest data that they can then sell. That is why University of Groningen computer scientist Fadi Mohsen, together with colleagues from the University of Michigan-Flint (US) and the Palestinian An-Najah National University, has developed an algorithm that ranks similar apps on privacy scores. A description of the system was published in the journal Concurrency and Computation: Practice and Experience on 2 September.

When you are installing an app, it has to tell you which information it will access. ‘However, users don’t pay much attention to this as a rule,’ says Mohsen. ‘They are, generally speaking, the weakest link in privacy protection. That is why we wanted to develop a system to mitigate intrusive apps that reduces the reliance on the attention and understanding of the users.’ Functionality

Mohsen and his colleagues collected data on more than one million apps from the Google Play Store to use them in demo systems and experiments. ‘We rely on features that we extracted from the metadata of these apps and their configuration/manifest files. Additionally, we built a web-based interface to collect the privacy preferences of users.’ Their method is based on scoring applications on these features and on users’ preferences. The score reflects the intrusiveness behaviour of each application relative to other apps in the same category, and is used to rank the applications.

Next, the scientists built a trial search engine to find new apps, which incorporates their methodology. The apps that are shown on the top of the list are the least intrusive. Mohsen: ‘A normal search will rank the apps by their functionality. Our engine compares apps with similar functionalities on their privacy score.’ So the app at the top of the list will respect your privacy the most. Advertising

The ranking algorithm takes two scores into consideration: the score for permission, and that for listeners. The former determines how much access each application is granted on the user’s phone, such as reading SMS messages, use your default calendar and even deleting pictures. The latter gives the apps the ability to keep track of the occurrences on the user’s phone, such as whether the user is present or a new SMS message has arrived. ‘The information that is gathered by these free apps can be sold, for example to companies who produce targeted advertising,’ Mohsen explains. The system that he and his colleagues have devised could help users to avoid the most intrusive apps without having to read all of the privacy information.

The website and search engine were tested by a group of test subjects. ‘The results show that they found the system for setting up their permission preferences easy to use. They also said that they would value it if app stores took their preferences into account when recommending certain apps,’ says Mohsen. This shows that the approach is useful and would be effective in helping users to choose apps that respect their privacy. Google

Ideally, companies like Google could use this system in the search engine for their app store. However, another option is to create a website like the one built for this study, where users can express their preferences on privacy issues and then look for apps via the website’s search engine. Mohsen: ‘Such dedicated websites are quite normal these days, so the approach is viable.’

In the meantime, Mohsen is looking at other privacy issues. ‘We are developing a system that monitors apps after installation. In some cases, updates can require extra permissions from the users.’ In the end, the systems that he creates should give privacy-respecting apps an advantage over the more intrusive ones. ‘Our aim is to help app developers who respect the privacy of their users.’

Fadi Mohsen, Hamed Abdelhaq, Halil Bisgin:
Security-Centric Ranking Algorithm and Two Privacy Scores To Mitigate Intrusive Apps. Concurrency and Computation: Practice and Experience, 2021. doi: 10.1002/cpe.6571

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...