Explainer: What is differential privacy and how can it protect your data?

By adding random noise to the aggregate data, differential privacy can protect information about individual users while still providing accurate results from database queries.

The Conversation

This article was first posted on The Conversation.

It’s no secret that big tech companies like Facebook, Google, Apple and Amazon are increasingly infiltrating our personal and social interactions to collect vast amounts of data on us every day. At the same time, privacy violations in cyberspace regularly make front page news.

So how should privacy be protected in a world where data is gathered and shared with increasing speed and ingenuity?

Differential privacy is a new model of cybersecurity that proponents claim can protect personal data far better than traditional methods.

The math it is based on was developed 10 years ago, and the method has been adopted by Apple and Google in recent years.

What is differential privacy?

Differential privacy makes it possible for tech companies to collect and share aggregate information about user habits, while maintaining the privacy of individual users.

For example, say you wanted to show the most popular routes people take walking through a park. You track the routes of 100 people who regularly walk through the park, and whether they walk on the path or through the grass.But instead of sharing the specific people taking each route, you share the aggregate data collected over time. People viewing your results might know that 60 out of 100 people prefer to take a short-cut through the grass, but not which 60 people.

Why do we need it?

Many of the world’s governments have strict policies about how tech companies collect and share user data. Companies who do not follow the rules can face huge fines. A Belgian court recently ordered Facebook to stop collecting data on users’ browsing habits on external websites, or face fines of €250,000 a day.

For many companies, especially multinationals operating in different jurisdictions, this leaves them in a delicate position when it comes to the collection and use of customer data.

On the one hand, these companies need users’ data so they can provide high-quality services that benefit users, such as personalized recommendations. On the other hand, they may face charges if they collect too much user data, or if they try to move data from one jurisdiction to another.

Traditional privacy-preserving tools such as cryptography can’t resolve this dilemma since it prevents tech companies from accessing the data at all. And anonymity reduces the value of data -- an algorithm can’t serve you personalized recommendations if it doesn’t know what your habits are.

How does it work?

Let’s continue the example of walking routes through a park. If you know the identities of those included in the study, but you don’t know who took which route then you might assume that privacy is protected. But that may not be the case.

Say someone viewing your data wants to ascertain if Bob prefers to walk through the grass or on the path. They have obtained background information about the other 99 people in the study, which tells them that 40 people prefer to walk on the path and 59 prefer to walk through the grass. Therefore, they can deduce that Bob, who is the 100th person in the database, is the 60th person who prefers to walk through the grass.

This type of attack is a called a differentiated attack, and it is quite hard to defend against as you cannot control how much background knowledge someone can obtain. Differential privacy aims to defend against this type of attack.

Someone deducing your walking route might not sound too serious, but if you replace walking routes with HIV test results, then you can see there is potential for a serious invasion of privacy.

The differential privacy model guarantees that even if someone has complete information about 99 of 100 people in a data set, they still cannot deduce the information about the final person.

The primary mechanism to achieve that is to add random noise to the aggregate data. In the path example, you may say the number of people who prefer to cross the grass is 59 or 61, rather than exact number of 60. The inaccurate number can preserve the privacy of Bob, but it will have very little impact on the pattern: around 60% people prefer to take a short-cut.

The noise is carefully designed. When Apple employed differential privacy in iOS 10, it added noise to individual user inputs. That means it can track, for example, the most frequently used emojis, but the emoji usage of any individual user is masked.

Cynthia Dwork, the inventor of the differential privacy, has proposed wonderful mathematical proofs on how much noise is enough to achieve the requirement of differential privacy.

What are its practical applications?

Differential privacy can be applied to everything from recommendation systems to location-based services and social networks. Apple uses differential privacy to gather anonymous usage insights from devices like iPhones, iPads and Macs. The method is user-friendly, and legally in the clear.

Differential privacy would also allow a company like Amazon access your personalized shopping preferences while hiding sensitive information about your historical purchase list. Facebook could use it to collect behavioral data for targeted advertising, without violating a country’s privacy policies.

How could it be used in the future?

Different countries have varying privacy policies, and sensitive documents currently have to be manually checked before they move from one country to another. This is time-consuming and expensive.

Recently, a team from Deakin University developed differential privacy technology to automate privacy processes within cloud-sharing communities across countries.

They propose using mathematical formulas to model the privacy laws of each country that could be translated to “middleware” (software) to ensure the data conforms. Employing differential privacy in this way could protect the privacy of users and resolve a data sharing headache for tech companies.

X
This website uses cookies to enhance user experience and to analyze performance and traffic on our website. We also share information about your use of our site with our social media, advertising and analytics partners. Learn More / Do Not Sell My Personal Information
Accept Cookies
X
Cookie Preferences Cookie List

Do Not Sell My Personal Information

When you visit our website, we store cookies on your browser to collect information. The information collected might relate to you, your preferences or your device, and is mostly used to make the site work as you expect it to and to provide a more personalized web experience. However, you can choose not to allow certain types of cookies, which may impact your experience of the site and the services we are able to offer. Click on the different category headings to find out more and change our default settings according to your preference. You cannot opt-out of our First Party Strictly Necessary Cookies as they are deployed in order to ensure the proper functioning of our website (such as prompting the cookie banner and remembering your settings, to log into your account, to redirect you when you log out, etc.). For more information about the First and Third Party Cookies used please follow this link.

Allow All Cookies

Manage Consent Preferences

Strictly Necessary Cookies - Always Active

We do not allow you to opt-out of our certain cookies, as they are necessary to ensure the proper functioning of our website (such as prompting our cookie banner and remembering your privacy choices) and/or to monitor site performance. These cookies are not used in a way that constitutes a “sale” of your data under the CCPA. You can set your browser to block or alert you about these cookies, but some parts of the site will not work as intended if you do so. You can usually find these settings in the Options or Preferences menu of your browser. Visit www.allaboutcookies.org to learn more.

Sale of Personal Data, Targeting & Social Media Cookies

Under the California Consumer Privacy Act, you have the right to opt-out of the sale of your personal information to third parties. These cookies collect information for analytics and to personalize your experience with targeted ads. You may exercise your right to opt out of the sale of personal information by using this toggle switch. If you opt out we will not be able to offer you personalised ads and will not hand over your personal information to any third parties. Additionally, you may contact our legal department for further clarification about your rights as a California consumer by using this Exercise My Rights link

If you have enabled privacy controls on your browser (such as a plugin), we have to take that as a valid request to opt-out. Therefore we would not be able to track your activity through the web. This may affect our ability to personalize ads according to your preferences.

Targeting cookies may be set through our site by our advertising partners. They may be used by those companies to build a profile of your interests and show you relevant adverts on other sites. They do not store directly personal information, but are based on uniquely identifying your browser and internet device. If you do not allow these cookies, you will experience less targeted advertising.

Social media cookies are set by a range of social media services that we have added to the site to enable you to share our content with your friends and networks. They are capable of tracking your browser across other sites and building up a profile of your interests. This may impact the content and messages you see on other websites you visit. If you do not allow these cookies you may not be able to use or see these sharing tools.

If you want to opt out of all of our lead reports and lists, please submit a privacy request at our Do Not Sell page.

Save Settings
Cookie Preferences Cookie List

Cookie List

A cookie is a small piece of data (text file) that a website – when visited by a user – asks your browser to store on your device in order to remember information about you, such as your language preference or login information. Those cookies are set by us and called first-party cookies. We also use third-party cookies – which are cookies from a domain different than the domain of the website you are visiting – for our advertising and marketing efforts. More specifically, we use cookies and other tracking technologies for the following purposes:

Strictly Necessary Cookies

We do not allow you to opt-out of our certain cookies, as they are necessary to ensure the proper functioning of our website (such as prompting our cookie banner and remembering your privacy choices) and/or to monitor site performance. These cookies are not used in a way that constitutes a “sale” of your data under the CCPA. You can set your browser to block or alert you about these cookies, but some parts of the site will not work as intended if you do so. You can usually find these settings in the Options or Preferences menu of your browser. Visit www.allaboutcookies.org to learn more.

Functional Cookies

We do not allow you to opt-out of our certain cookies, as they are necessary to ensure the proper functioning of our website (such as prompting our cookie banner and remembering your privacy choices) and/or to monitor site performance. These cookies are not used in a way that constitutes a “sale” of your data under the CCPA. You can set your browser to block or alert you about these cookies, but some parts of the site will not work as intended if you do so. You can usually find these settings in the Options or Preferences menu of your browser. Visit www.allaboutcookies.org to learn more.

Performance Cookies

We do not allow you to opt-out of our certain cookies, as they are necessary to ensure the proper functioning of our website (such as prompting our cookie banner and remembering your privacy choices) and/or to monitor site performance. These cookies are not used in a way that constitutes a “sale” of your data under the CCPA. You can set your browser to block or alert you about these cookies, but some parts of the site will not work as intended if you do so. You can usually find these settings in the Options or Preferences menu of your browser. Visit www.allaboutcookies.org to learn more.

Sale of Personal Data

We also use cookies to personalize your experience on our websites, including by determining the most relevant content and advertisements to show you, and to monitor site traffic and performance, so that we may improve our websites and your experience. You may opt out of our use of such cookies (and the associated “sale” of your Personal Information) by using this toggle switch. You will still see some advertising, regardless of your selection. Because we do not track you across different devices, browsers and GEMG properties, your selection will take effect only on this browser, this device and this website.

Social Media Cookies

We also use cookies to personalize your experience on our websites, including by determining the most relevant content and advertisements to show you, and to monitor site traffic and performance, so that we may improve our websites and your experience. You may opt out of our use of such cookies (and the associated “sale” of your Personal Information) by using this toggle switch. You will still see some advertising, regardless of your selection. Because we do not track you across different devices, browsers and GEMG properties, your selection will take effect only on this browser, this device and this website.

Targeting Cookies

We also use cookies to personalize your experience on our websites, including by determining the most relevant content and advertisements to show you, and to monitor site traffic and performance, so that we may improve our websites and your experience. You may opt out of our use of such cookies (and the associated “sale” of your Personal Information) by using this toggle switch. You will still see some advertising, regardless of your selection. Because we do not track you across different devices, browsers and GEMG properties, your selection will take effect only on this browser, this device and this website.