準同型暗号で暗号化したままAI推論を実行する、GoogleのHEIR

"Today we're excited to showcase HEIR, the latest powerful tool added to our Private Computing Toolkit. HEIR is an open source compiler that unlocks cryptographically-secure private AI inference."／"However, manually converting an existing program to use homomorphic encryption efficiently requires a team of cryptographers."／"To overcome the usability challenges and advance the opportunity homomorphic encryption provides, researchers and engineers at Google built the HEIR compiler project. HEIR (Homomorphic Encryption Intermediate Representation) is an open-source compiler toolchain and development platform for homomorphic encryption. In particular, HEIR can convert pre-trained AI models that operate on unencrypted data to operate on encrypted inputs. Our vision is to make HEIR a one-click solution to enable non-experts to incorporate encrypted inference into production applications."／"Since announcing our intentions in 2023, we’ve seen the homomorphic encryption community embrace HEIR."（冒頭・Homomorphic encryption・About HEIR の節）— Google 公式ブログより

"HEIR is a compiler toolchain for fully homomorphic encryption (FHE). We aim to be the industry-standard compiler for FHE."（What is HEIR? の節）— HEIR 公式サイトより

"Standard protections like end-to-end encryption present a trade-off: user-data can be protected from data breaches, but then the service provider cannot provide features that depend on the data, such as spam or virus detection. Critical sectors like healthcare and finance are even more averse to these risks, and strict regulations limit data sharing across institutions. Alternative mechanisms to provide the same features, like local processing, are limited by the capabilities of the local device and the sensitivity of the service provider's IP. Shipping proprietary AI to a device risks leaking the model."／"A solution to these issues is homomorphic encryption, a rapidly maturing technology that fundamentally alters this trade-off by allowing computations to be performed directly on encrypted data. Servers can process ciphertexts and return encrypted results without exposing any underlying information. For example, a cloud service can provide content recommendations without being able to see the user's features. This is no exaggeration: one of the demos featured in this post does exactly this. But while homomorphic encryption has a nontrivial cost overhead, it shifts the capability/privacy trade-off to a question of cost. And the cost of homomorphic encryption is rapidly decreasing."／"Like private information retrieval, and in contrast to hardware-based solutions, homomorphic encryption's strong security and privacy guarantees are purely cryptographic."（いずれも Homomorphic encryption の節）— Google 公式ブログより

"To demonstrate how far homomorphic encryption has come, we’re sharing four private inference applications. Each application was compiled with HEIR, and latency numbers are presented for a single-threaded CPU. The source code for all examples is available in our GitHub repository."／"A Deep Learning Recommendation Model unlocks serving private content recommendations, joint work with Belfort Labs, LG, and New York University."／"Credit card fraud detection: Together with Niobium and hardshell.ai, we compiled a credit card fraud detector."／"Threat intrusion: Together with Niobium we compiled the Kitsune system for anomaly detection of encrypted network traffic. This allows a service provider to detect anomalies without revealing the contents of network packets to the service provider."／"Hotword Detector: Together with Belfort Labs we compiled a hotword detection model, which could allow an audio-triggered AI agent to recognize hotwords while protecting the privacy of the audio recordings."／"We have partnered with companies developing hardware accelerators for homomorphic encryption, including Belfort, Niobium, Cornami, and Optalysys. The fruits of those efforts are shown in our demos below, and we plan to demonstrate the latency benefits of these accelerators in the near future."（About HEIR・Applications of HEIR の節）— Google 公式ブログより

"For hardware designers, HEIR provides multiple layers of abstraction at which to integrate code generation. This allows HEIR to support code generation for hardware accelerators that implement high-level FHE operations like bootstrap, as well as accelerators that operate at lower-level polynomial arithmetic."（Why HEIR? の節）— HEIR 公式サイトより

"By building on HEIR, cryptographers can focus on their specific optimization and use the existing infrastructure for testing, benchmarking, and comparisons. This has resulted in collaborations with Georgia Tech, Carnegie Mellon, UC Santa Barbara, Illinois Institute of Technology, Purdue, the University of Edinburgh, Tsinghua University, and others. To date, four peer-reviewed publications were built on HEIR, with more in preparation, and HEIR has accumulated numerous citations."（About HEIR の節）— Google 公式ブログより

"Write a program in Python, annotate the types to mark which are secret, and HEIR will compile the rest."／"Compile high level programs to encrypted equivalents."／"Support all modern FHE schemes."／"Support code generation for FHE hardware accelerators, including GPU, TPU, FPGA, and custom ASICs."／"Support code generation for standard FHE libraries, such as OpenFHE and Lattigo."／"Support front-end languages for ease of development, such as Python and Torch."／"The HEIR codebase and documentation are maintained by Google."／"Discussing project proposals and designs on HEIR’s issues page."／"Improving or expanding HEIR’s documentation."／"Discussing project direction at HEIR’s regular working group meetings and office hours."（Why HEIR?・Project Goals・Contributing to HEIR・Disclaimers の節）— HEIR 公式サイトより

"As the software industry adapts to security and privacy changes amid AI, our research team is working to make homomorphic encryption, easy to develop, fast to run, and ubiquitous across industry."（末尾の段落）— Google 公式ブログより