Technique protects privacy when making online recommendations
Researchers devise an efficient protocol to keep a user’s private information secure when algorithms use it to recommend products, songs, or shows
Written by Adam Zewe, MIT News Office
Algorithms recommend products while we shop online or suggest songs we might like as we listen to music on streaming apps.
These algorithms work by using personal information like our past purchases and browsing history to generate tailored recommendations. The sensitive nature of such data makes preserving privacy extremely important, but existing methods for solving this problem rely on heavy cryptographic tools requiring enormous amounts of computation and bandwidth.
MIT researchers may have a better solution. They developed a privacy-preserving protocol that is so efficient it can run on a smartphone over a very slow network. Their technique safeguards personal data while ensuring recommendation results are accurate.
In addition to user privacy, their protocol minimizes the unauthorized transfer of information from the database, known as leakage, even if a malicious agent tries to trick a database into revealing secret information.
The new protocol could be especially useful in situations where data leaks could violate user privacy laws, like when a health care provider uses a patient’s medical history to search a database for other patients who had similar symptoms or when a company serves targeted advertisements to users under European privacy regulations.
“This is a really hard problem. We relied on a whole string of cryptographic and algorithmic tricks to arrive at our protocol,” says Sacha Servan-Schreiber, a graduate student in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and lead author of the paper that presents this new protocol.
Servan-Schreiber wrote the paper with fellow CSAIL graduate student Simon Langowski and their advisor and senior author Srinivas Devadas, the Edwin Sibley Webster Professor of Electrical Engineering. The research will be presented at the IEEE Symposium on Security and Privacy.
The data next door
The technique at the heart of algorithmic recommendation engines is known as a nearest neighbor search, which involves finding the data point in a database that is closest to a query point. Data points that are mapped nearby share similar attributes and are called neighbors.
These searches involve a server that is linked with an online database which contains concise representations of data point attributes. In the case of a music streaming service, those attributes, known as feature vectors, could be the genre or popularity of different songs.
To find a song recommendation, the client (user) sends a query to the server that contains a certain feature vector, like a genre of music the user likes or a compressed history of their listening habits. The server then provides the ID of a feature vector in the database that is closest to the client’s query, without revealing the actual vector. In the case of music streaming, that ID would likely be a song title. The client learns the recommended song title without learning the feature vector associated with it.
“The server has to be able to do this computation without seeing the numbers it is doing the computation on. It can’t actually see the features, but still needs to give you the closest thing in the database,” says Langowski.
To achieve this, the researchers created a protocol that relies on two separate servers that access the same database. Using two servers makes the process more efficient and enables the use of a cryptographic technique known as private information retrieval. This technique allows a client to query a database without revealing what it is searching for, Servan-Schreiber explains.
Overcoming security challenges
But while private information retrieval is secure on the client side, it doesn’t provide database privacy on its own. The database offers a set of candidate vectors — possible nearest neighbors — for the client, which are typically winnowed down later by the client using brute force. However, doing so can reveal a lot about the database to the client. The additional privacy challenge is to prevent the client from learning those extra vectors.
The researchers employed a tuning technique that eliminates many of the extra vectors in the first place, and then used a different trick, which they call oblivious masking, to hide any additional data points except for the actual nearest neighbor. This efficiently preserves database privacy, so the client won’t learn anything about the feature vectors in the database.
Once they designed this protocol, they tested it with a nonprivate implementation on four real-world datasets to determine how to tune the algorithm to maximize accuracy. Then, they used their protocol to conduct private nearest neighbor search queries on those datasets.
Their technique requires a few seconds of server processing time per query and less than 10 megabytes of communication between the client and servers, even with databases that contained more than 10 million items. By contrast, other secure methods can require gigabytes of communication or hours of computation time. With each query, their method achieved greater than 95 percent accuracy (meaning that nearly every time it found the actual approximate nearest neighbor to the query point).
The techniques they used to enable database privacy will thwart a malicious client even if it sends false queries to try and trick the server into leaking information.
“A malicious client won’t learn much more information than an honest client following protocol. And it protects against malicious servers, too. If one deviates from protocol, you might not get the right result, but they will never learn what the client’s query was,” Langowski says.
In the future, the researchers plan to adjust the protocol so it can preserve privacy using only one server. This could enable it to be applied in more real-world situations, since it would not require the use of two noncolluding entities (which don’t share information with each other) to manage the database.
Innovative Ideas and Breakthroughs from NMIMS MPSTME Civil Engineering
The department has published two patents, research papers at international conferences
The Civil Engineering department of NMIMS MPSTME has been making significant strides in the field of disaster management, flood resilience, and sustainable infrastructure. The department has published two patents, research papers at international conferences, and completed several student-led projects on topics such as renewable energy, groundwater modelling, and self-healing concrete.
The first patent, ‘Automated Flood Water Regulating Multipurpose System,’ proposes a novel approach to flood resilience by constructing multipurpose wells on the banks of rivers to discharge excess water and generate hydropower. The second patent, ‘Aqua Barrier,’ is an automated mechanism that can protect any flood-prone area, regardless of its size, from any disasters caused due to water.
The student-led projects are equally impressive, with topics ranging from low-volume rural concrete roads to oscillating tidal wave energy converters. These projects showcase the department’s focus on sustainable infrastructure, renewable energy, and innovative design.
The faculty at NMIMS MPSTME Civil Engineering department, led by Head, Dr. Meenal Mategaonkar and Research coordinator, Dr. Jigisha Vashi, played a vital role in guiding and mentoring students toward research excellence. Their expertise and guidance have enabled students to participate and win awards in prestigious competitions such as the CDRI’s ‘Imagining Disaster Resilient Structures’ and The University of Queensland’s ‘Engineering Design Challenge, and AAKAR at IIT Bombay.’
The department’s success is further evidenced by the achievements of its students in national and international conferences. Students presented their research papers in Scopus Indexed papers and conferences such as the 9th Indian Young Geotechnical Engineering Conference and the Eighth Indian Young Geotechnical Conference.
Dr. Meenal Mategaonkar, Head of the Civil Engineering Department, MPSTME, NMIMS, said, “The achievements of the NMIMS MPSTME Civil Engineering department demonstrate its commitment to developing innovative solutions for complex problems in the field of civil engineering. The department’s focus on sustainable infrastructure, disaster resilience, and renewable energy is essential for addressing the challenges faced by society today. It is a testament to the hard work and dedication of both students and faculty and their commitment to excellence.”
Embark on a Journey of Scientific Empowerment with NMIMS School of Science’s Innovative Programs!
The school is known for its strong emphasis on academic excellence, research, and innovation, and is recognized as one of the leading science schools in the country
SVKM’s NMIMS Sunandan Divatia School of Science (SDSOS) has officially announced the commencement of the admissions process for its Bachelors, Masters and Doctoral programs. The school is known for its strong emphasis on academic excellence, research, and innovation, and is recognized as one of the leading science schools in the country.
Aspiring students who are interested in pursuing a career in the field of science can now apply for various undergraduate, postgraduate, and doctoral programs offered by SDSOS. The Bachelor of Science (B.Sc.) programs are available in Applied Psychology, Biomedical Science, and Animation and VFX, while the Master of Science (M.Sc.) programs are offered in Chemistry, Biological Sciences, Applied Psychology, and Physiotherapy. The school also offers Ph.D. program in Science with various disciplines such as Chemistry, and Biological Sciences.
With a focus on creating industry-ready and research-savvy graduates, SDSOS has been at the forefront of imparting cutting-edge knowledge and practical skills through constantly evolving curriculums and state-of-the-art facilities and is situated in the heart of Mumbai.
Dr. Purvi Bhatt, I/C Dean, Sunandan Divatia School of Science, said, “The school provides a dynamic and inclusive learning environment that fosters creativity, critical thinking, and innovation. Our interdisciplinary approach to education prepares students for successful careers in science and beyond, while our emphasis on co-curricular and extracurricular activities ensures their holistic development.”
The school has a student-centric environment that supports research in niche areas of Science & Technology, state-of-the-art infrastructure, and equipment to enhance students’ hands-on skills, and a library facility that is constantly updated with the latest information. The labs at SDSOS provide modernised infrastructure and the latest equipment such as the animal tissue culture lab and the wet labs at the department of Biological Sciences offer cutting-edge technology to mould students into scientists.
School of Science offers a wide range of opportunities for students to explore their talents and interests, as well as gain valuable practical experience. The events and activities mentioned, such as Excalibur, National Science Day, Open day, Guest talks, Book Talk, Sports Day, Psych Film Fest, and club activities like photography and art, these programs provide a platform for students to demonstrate their abilities and gain insights from their peers.
The Future of Architecture Takes Center Stage at NMIMS BSSA
Leach is a co-founder of Digital FUTURES and an academician at the Academy of Europe
NMIMS Balwant Sheth School of Architecture was excited to host Open Studio 2022-23 program by the renowned architectural theorist and digital design expert, Neil Leach, on 28th March 2023 and the title was, “Tell me that AI ain’t scary”
Leach is a co-founder of Digital FUTURES and an academician at the Academy of Europe. Leach has published over 40 books on architectural theory and digital design, including “Architecture in the Age of Artificial Intelligence: An Introduction to AI for Architects” and “The AI Design Revolution: How AI Will Transform Architecture.”
In the lecture, Leach highlighted the potential threat that artificial intelligence (AI) poses to the field of architecture. With the recent launch of GPT4 and the growing capabilities of AI, there is concern among architects that their jobs may be at risk. Leach provided an informed overview of the current state of AI and its potential impact on the architecture profession.
“We are very happy and proud to host Professor Neil Leach at the school. As a leading school of architecture, we are committed to providing our students with a comprehensive education that equips them with the skills and knowledge needed to thrive in the rapidly evolving field of design. Our Open Studio program and public lectures, and talks by experts like Neil Leach, play a critical role in this mission by enabling students to learn from distinguished scholars and practitioners and engage with cutting-edge ideas and technologies. We are excited to continue providing these opportunities and look forward to seeing the impact they will have on the future of architecture and design,” said, BSSA Dean, Dr. Kaiwan Mehta. As the field of architecture continues to evolve, it is essential to stay informed about emerging technologies and their potential impact on the profession. NMIMS BSSA School enables students to learn from experts and engage with pressing issues in architecture and design. By inviting renowned scholars and practitioners like Neil Leach to share their insights and expertise, the school provides a valuable opportunity for students to expand their knowledge and deepen their understanding of the field.
Business & Economy1 year ago
NSE Academy Limited collaborates with HDFC Mutual Fund for financial awareness program
Edu News2 months ago
Innovative Ideas and Breakthroughs from NMIMS MPSTME Civil Engineering
Science & Technology2 months ago
3D-printed revolving devices can sense how they are moving
Business & Economy10 months ago
Using artificial intelligence to control digital manufacturing
Edu News12 months ago
Astronomers discover a multiplanet system nearby
Edu News12 months ago
Stronger security for smart devices
Edu News1 year ago
Search reveals eight new sources of black hole echoes
Edu News10 months ago
Russian Edu Fair Held