Encrypted advertising recommendations
Seed Round $6M: Building the Next Era of Encrypted Computing.
TechnologyCompanyCareers
CONTACT US
About<br>Blog<br>Technology
contact us
Technology<br>About<br>Blog
contact us
Announcements
Encrypted advertising recommendations<br>4/8/25<br>Marc Desgroseilliers
What if a recommendation engine could know exactly what to show you, without knowing anything about you? Research from LG Electronics' Emerging Technology Lab, together with NYU and Belfort, brings that closer than most people expect. New LG-NYU algorithms cut encrypted embedding lookups by 56x, but reaching near real-time speed took Belfort's GPU acceleration platform, which delivered a further 400x speedup and brought recommendation latency down to 0.56 seconds, from nearly four minutes. User data is never decrypted and nothing is exposed to the server, so personalization no longer has to come at the cost of privacy.<br>Recommendations That Learn Nothing About You<br>Every day, companies collect more data about what you buy, watch, and click. That data is what makes a recommendation feel useful instead of random. But that same data is also deeply private, and regulators across Europe and beyond keep tightening the rules on how far advertisers can reach into a person's life. The old trade-off was uncomfortable: better recommendations meant handing over more of your personal information.<br>Researchers at LG Electronics, Emerging Technology Lab, have been exploring how privacy-preserving technologies can enable personalized advertising recommendations while maintaining strong privacy guarantees. As part of an ongoing research effort, the team, in collaboration with NYU, developed new algorithmic techniques for encrypted recommendation inference and partnered with Belfort to evaluate how hardware acceleration could make these approaches more practical.<br>In this post, we discuss how LG-NYU’s encrypted recommendation algorithms were combined with Belfort's acceleration platform, the resulting performance improvements, and what this means for the future of privacy-preserving AI.<br>The Challenge: Recommendations Without Invading Privacy<br>A recommendation engine learns from your behaviour. Feed it enough signals about your persona, such as age, browsing history, location, and your activities, and it gets good at making personalized recommendations. The catch is that those signals sit on a server, readable by the company that holds them and exposed to anyone who breaches it.<br>Encrypted computing or Fully Homomorphic Encryption (FHE) changes the rules. It lets a server compute directly on encrypted data without ever decrypting it. The user encrypts their information before it leaves their device. The server produces a recommendation on data it cannot read. The encrypted answer comes back, and only the user can unlock it. The company serves a relevant recommendation and learns nothing about the person it served, not their age, nor their browsing history nor their location.<br>For years FHE was treated as a beautiful idea that was far too slow to use. The work with LG Electronics and NYU was about proving that is no longer true.<br>Why Recommendation Models Are Hard to Encrypt<br>To see the difficulty, it helps to know what a recommendation model does under the hood.<br>A canonical architecture is the Deep Learning Recommendation Model, or DLRM, which Meta open-sourced in 2019.<br>It handles two kinds of input. Dense features are plain numbers, like the time of day or how often you visit. Sparse features are categories, like a product ID or a country, and each one can have tens of thousands of possible values.<br>A model cannot use a category directly, because its ID is a name, not a number you can do math on. Product four million is not "twice" product two million; the IDs are arbitrary, so the model needs a different representation. To work around this, the model keeps an embedding table: a large lookup table where every category has its own row of learned numbers describing how that category behaves. The model looks up the right row for each sparse feature, runs the dense features through a small neural network, and combines everything to predict how likely you are to click.<br>The embedding lookup is what makes encryption painful. On normal data, grabbing one row is instant; the server jumps to it and ignores the rest. Under encryption the server is not allowed to know which row you want, because the row index is itself private and would reveal some information to the server. The only way to select a row blindly is to run encrypted math against every row in the table and let the arithmetic cancel out all but the one you asked for. Retrieving a single row means touching all of them and that is the bottleneck.<br>Algorithmic Optimizations: Faster in Software<br>The first gains came from being smarter about that lookup, before any specialised hardware enters the picture.<br>To achieve a more optimal outcome, LG Electronics research team, in collaboration with Prof....