Preserving privacy in analyses of textual data

New "Mad Libs" technique for replacing words in individual sentences is grounded in metric differential privacy.

Amazon prides itself on being the most customer-centric company on earth. That means maintaining the highest possible standards of both security and privacy when dealing with customer data.

Next month, at the ACM Web Search and Data Mining (WSDM) Conference, my colleagues and I will describe a way to protect privacy during large-scale analyses of textual data supplied by customers. Our method works by, essentially, re-phrasing the customer-supplied text and basing analysis on the new phrasing, rather than on the customers’ own language.

Differential privacy

Questions about data privacy are frequently met with the answer “It’s anonymized! Identifying features have been scrubbed!” However, studies such as this one from MIT show that attackers can deanonymize data by correlating it with “side information” from other data sources.

Differential privacy is a way to calculate the probability that analysis of a data set will leak information about any individual in that data set. Within the differential-privacy framework, protecting privacy usually means adding noise to a data set, to make data related to specific individuals more difficult to trace. Adding noise often means a loss of accuracy in data analyses, and differential privacy also provides a way to quantify the trade-off between privacy and accuracy.

Embedding space-phone.png
The researchers' technique adds noise (green) to the embedding of a word (orange) from a textual data set, producing a new point in the embedding space. Then it finds the valid embedding nearest that point — in this case, the embedding for the word "mobile".
Stacy Reilly

Let’s say that you have a data set of cell phone location traces for a particular city, and you want to estimate the residents’ average commute time. The data set contains (anonymized) information about specific individuals, but the analyst is interested only in an aggregate figure — 37 minutes, say.

Differential privacy provides a statistical assurance that the aggregate figure will not leak information about which individuals are in the data set. Say there are two data sets that are identical, except that one includes Alice’s data and one doesn’t. Differential privacy says that, given the result of an analysis — the aggregate figure — the probabilities that either of the two data sets was the basis of the analysis should be virtually identical.

Of course, the smaller the data set, the more difficult this standard is to meet. If the data set contains nine people with 15-minute commutes and one person, Bob, with a two-hour commute, the average commute time is very different for data sets that do and do not contain Bob. Someone with side information — that Bob frequently posts Instagram photos from a location two hours outside the city — could easily determine whether Bob is included in the data set.

Adding noise to the data can blur the distinctions between analyses performed on slightly different data sets, but it can also reduce the utility of the analyses. A very small data set might require the addition of so much noise that analyses become essentially meaningless. But the expectation is that as the size of the data set grows, the trade-off between utility and privacy becomes more manageable.

Privacy in the space of word embeddings

In the field of natural-language processing, a word embedding is a mapping from the space of words into a vector space, i.e., the space of real numbers. Often, this mapping depends on the frequency with which words co-occur with each other, so that related words tend to cluster near each other in the space:

So how can we go about preserving privacy in such spaces? One possibility is to modify the original text such that its author cannot be identified, but the semantics are preserved. This means adding noise in the space of word embeddings. The result is sort of like a game of Mad Libs, where certain words are removed from a sentence and replaced with others.

While we can apply standard differential privacy in the space of word embeddings, doing so would lead to poor performance. Differential privacy requires that any data point in a data set can be replaced by any other, without an appreciable effect on the results of aggregate analyses. But we want to cast a narrower net, replacing a given data point only with one that lies near it in the semantic space. Hence we consider a more general definition known as “metric” differential privacy.

Metric differential privacy

I said that differential privacy requires that the probabilities that a statistic is derived from either of two data sets be virtually identical. But what does “virtually” mean? With differential privacy, the allowable difference between the probabilities is controlled by a parameter, epsilon, which the analyst must determine in advance. With metric differential privacy, the parameter is epsilon times the distance between the two data sets, according to some distance metric: the more similar the data sets are, the harder they must be to distinguish.

Initially, metric differential privacy was an attempt to extend the principle of differential privacy to location data. Protecting privacy means adding noise, but ideally, the noise should be added in a way that preserves aggregate statistics. With location data, that means overwriting particular locations with locations that aren’t too far away. Hence the need for a distance metric.

The application to embedded linguistic data should be clear. But there’s a subtle difference. With location data, adding noise to a location always produces a valid location — a point somewhere on the earth’s surface. Adding noise to a word embedding produces a new point in the representational space, but it’s probably not the location of a valid word embedding. So once we’ve identified such a point, we perform a search to find the nearest valid embedding. Sometimes the nearest valid embedding will be the original word itself; in that case, the original word is not overwritten.

Hyperboloid.png
A two-dimensional hyperboloid.

In our paper, we analyze the privacy implications of different choices of epsilon value. In particular, we consider, for a given epsilon value, the likelihood that any given word in a string of words will be overwritten and the number of semantically related words that fall within a fixed distance of each word in the embedding space. This enables us to make some initial arguments about what practical epsilon values might be.

Hyperbolic space

In November 2019, at the IEEE International Conference on Data Mining (ICDM), we presented a paper that, although it appeared first, is in fact a follow-up to our WSDM paper. In that paper, we describe an extension of our work on metric differential privacy to hyperbolic space.

The word-embedding space we describe in the WSDM paper is the standard Euclidean space. A two-dimensional Euclidean space is a plane. A two-dimensional hyperbolic space, by contrast, is curved.

Poincare disc.png
A two-dimensional projection of word embeddings in a hyperbolic space. More-general concepts cluster toward the center, more specific concepts toward the edges.

In hyperbolic space, as in Euclidean space, distance between embeddings indicates semantic similarity. But hyperbolic spaces have an additional degree of representational capacity: the different curvature of the space at different locations can indicate where embeddings fall in a semantic hierarchy.

So, for instance, the embeddings of the words “ibuprofen”, “medication”, and “drug” may lie near each other in the space, but their positions along the curve indicate which of them are more specific terms and which more general. This allows us to ensure that we are substituting more general terms for more specific ones, which makes personal data harder to extract.

In experiments, we applied the same metric-differential-privacy framework to hyperbolic spaces that we had applied to Euclidean space and observed 20-fold greater guarantees on expected privacy in the worst case.

Related content

US, WA, Seattle
We are a team of doers working passionately to apply cutting-edge advances in deep learning in the life sciences to solve real-world problems. As a Senior Applied Science Manager you will participate in developing exciting products for customers. Our team rewards curiosity while maintaining a laser-focus in bringing products to market. Competitive candidates are responsive, flexible, and able to succeed within an open, collaborative, entrepreneurial, startup-like environment. At the leading edge of both academic and applied research in this product area, you have the opportunity to work together with a diverse and talented team of scientists, engineers, and product managers and collaborate with others teams. Location is in Seattle, US Embrace Diversity Here at Amazon, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust Balance Work and Life Our team puts a high value on work-life balance. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives Mentor & Grow Careers Our team is dedicated to supporting new members. We have a broad mix of experience levels and tenures, and we’re building an environment that celebrates knowledge sharing and mentorship. Our senior members enjoy one-on-one mentoring and thorough, but kind, code reviews. We care about your career growth and strive to assign projects based on what will help each team member develop into a better-rounded engineer and enable them to take on more complex tasks in the future. Key job responsibilities • Manage high performing engineering and science teams • Hire and develop top-performing engineers, scientists, and other managers • Develop and execute on project plans and delivery commitments • Work with business, data science, software engineer, biological, and product leaders to help define product requirements and with managers, scientists, and engineers to execute on them • Build and maintain world-class customer experience and operational excellence for your deliverables
US, Virtual
The Amazon Economics Team is hiring Interns in Economics. We are looking for detail-oriented, organized, and responsible individuals who are eager to learn how to work with large and complicated data sets. Some knowledge of econometrics, as well as basic familiarity with Stata, R, or Python is necessary. Experience with SQL, UNIX, Sawtooth, and Spark would be a plus. These are full-time positions at 40 hours per week, with compensation being awarded on an hourly basis. You will learn how to build data sets and perform applied econometric analysis at Internet speed collaborating with economists, data scientists and MBAʼs. These skills will translate well into writing applied chapters in your dissertation and provide you with work experience that may help you with placement. Roughly 85% of interns from previous cohorts have converted to full time economics employment at Amazon. If you are interested, please send your CV to our mailing list at econ-internship@amazon.com.
US, WA, Seattle
Amazon internships are full-time (40 hours/week) for 12 consecutive weeks with start dates in May - July 2023. Our internship program provides hands-on learning and building experiences for students who are interested in a career in hardware engineering. This role will be based in Seattle, and candidates must be willing to work in-person. Corporate Projects (CPT) is a team that sits within the broader Corporate Development organization at Amazon. We seek to bring net-new, strategic projects to life by working together with customers and evolving projects from ZERO-to-ONE. To do so, we deploy our resources towards proofs-of-concept (POCs) and pilot programs and develop them from high-level ideas (the ZERO) to tangible short-term results that provide validating signal and a path to scale (the ONE). We work with our customers to develop and create net-new opportunities by relentlessly scouring all of Amazon and finding new and innovative ways to strengthen and/or accelerate the Amazon Flywheel. CPT seeks an Applied Science intern to work with a diverse, cross-functional team to build new, innovative customer experiences. Within CPT, you will apply both traditional and novel scientific approaches to solve and scale problems and solutions. We are a team where science meets application. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems.
US, WA, Seattle
Amazon internships are full-time (40 hours/week) for 12 consecutive weeks with start dates in May - July 2023. Our internship program provides hands-on learning and building experiences for students who are interested in a career in hardware engineering. This role will be based in Seattle, and candidates must be willing to work in-person. Corporate Projects (CPT) is a team that sits within the broader Corporate Development organization at Amazon. We seek to bring net-new, strategic projects to life by working together with customers and evolving projects from ZERO-to-ONE. To do so, we deploy our resources towards proofs-of-concept (POCs) and pilot programs and develop them from high-level ideas (the ZERO) to tangible short-term results that provide validating signal and a path to scale (the ONE). We work with our customers to develop and create net-new opportunities by relentlessly scouring all of Amazon and finding new and innovative ways to strengthen and/or accelerate the Amazon Flywheel. CPT seeks an Applied Science intern to work with a diverse, cross-functional team to build new, innovative customer experiences. Within CPT, you will apply both traditional and novel scientific approaches to solve and scale problems and solutions. We are a team where science meets application. A successful candidate will be a self-starter comfortable with ambiguity, strong attention to detail, and the ability to work in a fast-paced, ever-changing environment. As an Applied Science Intern, you will own the design and development of end-to-end systems. You’ll have the opportunity to create technical roadmaps, and drive production level projects that will support Amazon Science. You will work closely with Amazon scientists, and other science interns to develop solutions and deploy them into production. The ideal scientist must have the ability to work with diverse groups of people and cross-functional teams to solve complex business problems.
US, MA, Westborough
Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart team of doers that work passionately to apply cutting edge advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even imagine yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. Amazon Robotics is seeking interns and co-ops with a passion for robotic research to work on cutting edge algorithms for robotics. Our team works on challenging and high-impact projects, including allocating resources to complete a million orders a day, coordinating the motion of thousands of robots, autonomous navigation in warehouses, identifying objects and damage, and learning how to grasp all the products Amazon sells. We are seeking internship candidates with backgrounds in computer vision, machine learning, resource allocation, discrete optimization, search, and planning/scheduling. You will be challenged intellectually and have a good time while you are at it! Key job responsibilities • Identifying creative solutions for challenging research problems in robotics and computer vision • Developing software solutions to test hypotheses and demonstrate new functionality • Prototyping concepts to collect data and measure performance • Writing code and unit tests and integrating code with other software and hardware components • Utilizing Amazon Robotics and Amazon engineering tools, processes and technologies • Delivering a final presentation to managers and engineers on the successes and challenges of their internship and the business value they have contributed
US, CA, Palo Alto
The Amazon Search team creates powerful, customer-focused search solutions and technologies. Whenever a customer visits an Amazon site worldwide and types in a query or browses through product categories, Amazon Search services go to work. We design, develop, and deploy high performance, fault-tolerant distributed search systems used by millions of Amazon customers every day. We’re seeking a Principal Scientist with a deep expertise in Search Science. Your responsibilities will include everything from developing and prototyping innovative machine learning, and deep learning algorithms to implementing, testing, and supporting full solutions in a production environment. We are looking for innovators who can contribute to advancing search technology on what’s scientifically possible while remaining committed to creating world-class products. Joining this team, you’ll experience the benefits of working in a dynamic, entrepreneurial environment, while leveraging the resources of Amazon.com (AMZN), Earth's most customer-centric company one of the world's leading internet companies. We provide a highly customer-centric, team-oriented environment in our offices located in Palo Alto, California. Key job responsibilities As a hands-on leader of this team, you’ll be responsible for defining key research questions, identifying relevant data, adopting or proposing innovative machine learning solutions conducting rigorous experiments, publishing results and working with the engineering team to deploy these solutions. As a strategic leader, you will identify investment opportunities, develop long term strategies, and propose, prioritize and deliver on goals. You’ll also participate in organizational planning, hiring, mentorship and leadership development. You will be technically fearless and with a passion for building scalable science and engineering solutions. You will serve as a key scientific resource in full-cycle development (conception, design, implementation, testing to documentation, delivery, and maintenance). About the team Starting in 2009, the Visual Search & Augmented Reality team has thus far launched many visual search solutions on the Amazon App that use computer vision and machine learning/deep learning to help customers complete their shopping missions more easily; multiple internal teams at Amazon (devices, Kindle, Seller services, etc.) also use our libraries and APIs to deliver solutions to their own customers. We are a full stack shop, and our team capabilities cover the whole solution spectrum, ranging across applied science, large scale engineering services, product management, UX design, and mobile app development for iOS and Android.
US, MN, Minneapolis
AWS Central Economics is an interdisciplinary team on the cutting edge of economics, statistical analysis, and machine learning whose mission is to solve problems that have high risk with abnormally high returns. Our team leverages the strengths of our scientists to build solutions for some of the toughest business problems here at Amazon AWS. We are looking for an exceptionally talented, seasoned, and motivated Economist to manage a team of economists and data scientists to drive the science for AWS. Key job responsibilities Manage a team of economists and data scientists to deliver actionable economic analyses to business leaders, provide leadership on the economics and science used in the analyses, and engage with business leaders to identify challenges AWS faces that call for in-depth economic analyses and to ensure the analyses have their intended impact.
LU, Luxembourg
&ltHire Relocation Requisition - not for posting> Provides insights to leadership on improving Supply Chain cost and Speed by using Data Science and Analytics techniques. Build Dashboards and models to industrialize these findings at scale.
US, VA, Arlington
The People eXperience and Technology Central Science Team (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. We are looking for economists who are able to work with business partners to hone complex problems into specific, scientific questions, and test those questions to generate insights. The ideal candidate will work with engineers and computer scientists to estimate models and algorithms on large scale data, design pilots and measure their impact, and transform successful prototypes into improved policies and programs at scale. We are looking for creative thinkers who can combine a strong technical economic toolbox with a desire to learn from other disciplines, and who know how to execute and deliver on big ideas as part of an interdisciplinary technical team. Ideal candidates will work closely with business partners to develop science that solves the most important business challenges. They will work in a team setting with individuals from diverse disciplines and backgrounds. They will serve as an ambassador for science and a scientific resource for business teams, so that scientific processes permeate throughout the HR organization to the benefit of Amazonians and Amazon. Ideal candidates will own the data analysis, modeling, and experimentation that is necessary for estimating and validating models. They will work closely with engineering teams to develop scalable data resources to support rapid insights, and take successful models and findings into production as new products and services. They will be customer-centric and will communicate scientific approaches and findings to business leaders, listening to and incorporate their feedback, and delivering successful scientific solutions. Key job responsibilities Use causal inference methods to evaluate the impact of policies on employee outcomes. Examine how external labor market and economic conditions impact Amazon's ability to hire and retain talent. Use scientifically rigorous methods to develop and recommend career paths for employees. A day in the life Work with teammates to apply economic methods to business problems. This might include identifying the appropriate research questions, writing code to implement a DID analysis or estimate a structural model, or writing and presenting a document with findings to business leaders. Our economists also collaborate with partner teams throughout the process, from understanding their challenges, to developing a research agenda that will address those challenges, to help them implement solutions. About the team We are a multidisciplinary team that combines the talents of science and engineering to develop innovative solutions to make Amazon Earth's Best Employer.
US, WA, Seattle
The People eXperience and Technology Central Science Team (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, wellbeing, and the value of work to Amazonians. We are an interdisciplinary team that combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. We are looking for economists who are able to apply economic methods to address business problems. The ideal candidate will work with engineers and computer scientists to estimate models and algorithms on large scale data, design pilots and measure their impact, and transform successful prototypes into improved policies and programs at scale. We are looking for creative thinkers who can combine a strong technical economic toolbox with a desire to learn from other disciplines, and who know how to execute and deliver on big ideas as part of an interdisciplinary technical team. Ideal candidates will work in a team setting with individuals from diverse disciplines and backgrounds. They will work with teammates to develop scientific models and conduct the data analysis, modeling, and experimentation that is necessary for estimating and validating models. They will work closely with engineering teams to develop scalable data resources to support rapid insights, and take successful models and findings into production as new products and services. They will be customer-centric and will communicate scientific approaches and findings to business leaders, listening to and incorporate their feedback, and delivering successful scientific solutions. Key job responsibilities Use causal inference methods to evaluate the impact of policies on employee outcomes. Examine how external labor market and economic conditions impact Amazon's ability to hire and retain talent. Use scientifically rigorous methods to develop and recommend career paths for employees. A day in the life Work with teammates to apply economic methods to business problems. This might include identifying the appropriate research questions, writing code to implement a DID analysis or estimate a structural model, or writing and presenting a document with findings to business leaders. Our economists also collaborate with partner teams throughout the process, from understanding their challenges, to developing a research agenda that will address those challenges, to help them implement solutions. About the team We are a multidisciplinary team that combines the talents of science and engineering to develop innovative solutions to make Amazon Earth's Best Employer.