arXiv subjects

Jung Hee Cheon

Publications and source records attributed to Jung Hee Cheon.

12 recordsLinked to original sources

arXiv2026

Private Iris Recognition with High-Performance FHE

Among biometric verification systems, irises stand out because they offer high accuracy even in large-scale databases. For example, the World ID project aims to provide authentication to all humans via iris recognition, with millions already registered. Storing such biometric data raises privacy concerns, which can be addressed using privacy-enhancing techniques. Bloemen et al. describe a solution based on 2-out-of-3 Secret-Sharing Multiparty Computation (SS-MPC), for the World ID setup. In terms of security, unless an adversary corrupts 2~servers, the iris codes remain confidential and nothing leaks beyond the result of the computation. Their solution is able to match~$32$ users against a database of~$2^{22}$ iris codes in~$\approx 2$s , using~24 H100 GPUs, more than 40~communication rounds and $81$GB/party of data transferred (the timing assumes a network speed above~3Tb/s). In the present work, we explore the use of Threshold Fully Homomorphic Encryption (ThFHE) for the same task. The ThFHE solution brings a number of security advantages: no trusted setup, the encrypted database and queries can be public, the secret can be distributed among many parties, and active security can be added without significant performance degradation. Our proof-of-concept implementation of the computation phase handles $32$~eyes against a database of $7\cdot 2^{14}$ iris codes in~$\approx 1.8$s ($\approx 0.33s$ for 4 eyes against the same database), using 8 RTX-5090 GPUs. To this, one should add~2 to 3 rounds of communication (depending on deployment choice). We perform the matching using the CKKS (Th)FHE scheme. Our main technical ingredients are the use of recent progress on FHE-based linear algebra boosted using int8 GPU operations, and the introduction of a technique reducing the number of ciphertexts to be processed as early as possible.

cs.CR↗

arXiv2026

Scaling up FHE-based Privacy-Preserving ML: Higher Throughput, Longer Inputs for LLama-3-8B

As large language models (LLMs) become ubiquitous, privacy concerns pertaining to inference keep growing. Fully homomorphic encryption (FHE) has emerged as a primary cryptographic solution for non-interactive confidential LLM inference. However, existing solutions scale poorly with input token length, focusing on small models or input sizes. They also suffer from large outlier values, which strongly impact the evaluation of non-linear layers, leading to heavy polynomial approximation costs. We scale up FHE-based LLM inference in two directions. First, we accelerate FHE-based inference for 128 encrypted tokens. We adopt ML techniques (token prepending and orthogonal rotations) to mitigate outlier impacts on the FHE evaluation of non-linear layers. Separately, we devise a novel polynomial evaluation method for sparsely-packed ciphertexts to speed up our homomorphic SoftMax implementation. We combine these with recent fast homomorphic linear algebra techniques, achieving significantly improved efficiency. Second, we expand the prompt size up to thousands of tokens for contexts where only the final part of the input is sensitive and encrypted. Processing this requires handling standard plaintext-plaintext and ciphertext-ciphertext components, alongside a wide homomorphic computation for a novel plaintext-ciphertext component. To address this, we devise a dedicated homomorphic linear algebra algorithm, building a shallow homomorphic attention circuit that minimizes bootstrapping costs. Based on these ingredients, we present a CKKS-based end-to-end implementation of Llama-3-8B private inference. On 8 NVIDIA RTX PRO 6000 GPUs, 128 encrypted tokens take 20s for summarization and 18s/token for generation (vastly outperforming the SOTA 295s on costlier H100 GPUs). For a heterogeneous 4096-token input (last 128 encrypted), it takes 64s for summarization and 22s/token for generation.

cs.CR↗

arXiv2026

Private Embedding Lookup with Encrypted Compact Queries under Fully Homomorphic Encryption

Many NLP or recommendation models begin by mapping discrete client inputs to embedding vectors. Since inputs can reveal sensitive information, the embedding step must be protected in privacy-preserving inference. Fully Homomorphic Encryption (FHE) enables inference over encrypted client data, but turns embedding lookup from simple table access into homomorphic computation. To keep the embedding table server-side and avoid transmitting encrypted embedding vectors from the client, we focus on server-side lookup: the client sends only a small encrypted index. Prior ICML 2024 work first builds a one-hot vector from the encrypted index before multiplying with the embedding table, and this one-hot generation is the dominant cost. One-hot-based methods are expensive in FHE: they construct a p-dimensional selection vector via an equality test for each coordinate, requiring $O(p \log p)$ total homomorphic operations. Our key observation is that private embedding lookup only requires a linearly independent representation of the encrypted index, not the one-hot basis itself. Building on it, we propose Independent Vector Evaluation (IVE). Instead of constructing a one-hot vector, IVE evaluates a linearly independent vector built from successive powers of a single encrypted value, reducing vector-generation cost to $O(p)$. It then recovers the same embedding vector via a precomputed change of basis, instantiated with an orthogonal Discrete Cosine Transform to mitigate error amplification. Our implementation shows IVE improves amortized lookup time by up to 78.4x over prior method. We further evaluate its impact on end-to-end encrypted FastText inference, where embedding lookup is a major cost in the shallow model. On Enron-Spam dataset, replacing one-hot generation with IVE reduces the share of vector generation in encrypted inference time from 99.6% to 66.3%.

cs.CR↗

arXiv2026

Fast Homomorphic Linear Algebra with BLAS

Homomorphic encryption is a cryptographic paradigm allowing to compute on encrypted data, opening a wide range of applications in privacy-preserving data manipulation, notably in AI. Many of those applications require significant linear algebra computations (matrix-vector products, and matrix-matrix products). This central role of linear algebra computations goes far beyond homomorphic algebra and applies to most areas of scientific computing. This high versatility led, over time, to the development of a set of highly optimized routines, specified in 1979 under the name BLAS (basic linear algebra subroutines). Motivated both by the applicative importance of homomorphic linear algebra and the access to highly efficient implementations of cleartext linear algebra able to draw the most out of available hardware, we explore the connections between CKKS-based homomorphic linear algebra and floating-point plaintext linear algebra. The CKKS homomorphic encryption system is the most natural choice in this setting, as it natively handles real numbers and offers a large SIMD parallelism. We provide reductions for matrix-vector products, vector-vector products for moderate-sized to large matrices to their plaintext equivalents. Combined with BLAS, we demonstrate that the efficiency loss between CKKS-based encrypted square matrix multiplication and double-precision floating-point square matrix multiplication is a mere 4-12 factor, depending on the precise situation.

cs.CR↗

arXiv2025

Cryptanalysis on Lightweight Verifiable Homomorphic Encryption

Verifiable Homomorphic Encryption (VHE) is a cryptographic technique that integrates Homomorphic Encryption (HE) with Verifiable Computation (VC). It serves as a crucial technology for ensuring both privacy and integrity in outsourced computation, where a client sends input ciphertexts ct and a function f to a server and verifies the correctness of the evaluation upon receiving the evaluation result f(ct) from the server. At CCS, Chatel et al. introduced two lightweight VHE schemes: Replication Encoding (REP) and Polynomial Encoding (PE). A similar approach to REP was used by Albrecht et al. in Eurocrypt to develop a Verifiable Oblivious PRF scheme (vADDG). A key approach in these schemes is to embed specific secret information within HE ciphertexts to verify homomorphic evaluations. This paper presents efficient attacks that exploit the homomorphic properties of encryption schemes. The one strategy is to retrieve the secret information in encrypted state from the input ciphertexts and then leverage it to modify the resulting ciphertext without being detected by the verification algorithm. The other is to exploit the secret embedding structure to modify the evaluation function f into f' which works well on input values for verification purposes. Our forgery attack on vADDG demonstrates that the proposed 80-bit security parameters in fact offer less than 10-bits of concrete security. Our attack on REP and PE achieves a probability 1 attack with linear time complexity when using fully homomorphic encryption.

cs.CR↗

arXiv2025

Encryption-Friendly LLM Architecture

Large language models (LLMs) offer personalized responses based on user interactions, but this use case raises serious privacy concerns. Homomorphic encryption (HE) is a cryptographic protocol supporting arithmetic computations in encrypted states and provides a potential solution for privacy-preserving machine learning (PPML). However, the computational intensity of transformers poses challenges for applying HE to LLMs. In this work, we propose a modified HE-friendly transformer architecture with an emphasis on inference following personalized (private) fine-tuning. Utilizing LoRA fine-tuning and Gaussian kernels, we achieve significant computational speedups -- 6.94x for fine-tuning and 2.3x for inference -- while maintaining performance comparable to plaintext models. Our findings provide a viable proof of concept for offering privacy-preserving LLM services in areas where data protection is crucial. Our code is available on GitHub.

cs.CR↗

arXiv2025

NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrapping

Fully homomorphic encryption (FHE) is a promising cryptographic primitive for realizing private neural network inference (PI) services by allowing a client to fully offload the inference task to a cloud server while keeping the client data oblivious to the server. This work proposes NeuJeans, an FHE-based solution for the PI of deep convolutional neural networks (CNNs). NeuJeans tackles the critical problem of the enormous computational cost for the FHE evaluation of CNNs. We introduce a novel encoding method called Coefficients-in-Slot (CinS) encoding, which enables multiple convolutions in one HE multiplication without costly slot permutations. We further observe that CinS encoding is obtained by conducting the first several steps of the Discrete Fourier Transform (DFT) on a ciphertext in conventional Slot encoding. This property enables us to save the conversion between CinS and Slot encodings as bootstrapping a ciphertext starts with DFT. Exploiting this, we devise optimized execution flows for various two-dimensional convolution (conv2d) operations and apply them to end-to-end CNN implementations. NeuJeans accelerates the performance of conv2d-activation sequences by up to 5.68 times compared to state-of-the-art FHE-based PI work and performs the PI of a CNN at the scale of ImageNet within a mere few seconds.

cs.CR↗

arXiv2024

SIMD-Aware Homomorphic Compression and Application to Private Database Query

In a private database query scheme (PDQ), a server maintains a database, and users send queries to retrieve records of interest from the server while keeping their queries private. A crucial step in PDQ protocols based on homomorphic encryption is homomorphic compression, which compresses encrypted sparse vectors consisting of query results. In this work, we propose a new homomorphic compression scheme with PDQ as its main application. Unlike existing approaches, our scheme (i) can be efficiently implemented by fully exploiting homomorphic SIMD technique and (ii) enjoys both asymptotically optimal compression rate and asymptotically good decompression complexity. Experimental results show that our approach is 4.7x to 33.2x faster than the previous best results.

cs.CR↗

arXiv2023

Toward Practical Privacy-Preserving Convolutional Neural Networks Exploiting Fully Homomorphic Encryption

Incorporating fully homomorphic encryption (FHE) into the inference process of a convolutional neural network (CNN) draws enormous attention as a viable approach for achieving private inference (PI). FHE allows delegating the entire computation process to the server while ensuring the confidentiality of sensitive client-side data. However, practical FHE implementation of a CNN faces significant hurdles, primarily due to FHE's substantial computational and memory overhead. To address these challenges, we propose a set of optimizations, which includes GPU/ASIC acceleration, an efficient activation function, and an optimized packing scheme. We evaluate our method using the ResNet models on the CIFAR-10 and ImageNet datasets, achieving several orders of magnitude improvement compared to prior work and reducing the latency of the encrypted CNN inference to 1.4 seconds on an NVIDIA A100 GPU. We also show that the latency drops to a mere 0.03 seconds with a custom hardware design.

cs.CR↗

arXiv2022

Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption

Embeddings, which compress information in raw text into semantics-preserving low-dimensional vectors, have been widely adopted for their efficacy. However, recent research has shown that embeddings can potentially leak private information about sensitive attributes of the text, and in some cases, can be inverted to recover the original input text. To address these growing privacy challenges, we propose a privatization mechanism for embeddings based on homomorphic encryption, to prevent potential leakage of any piece of information in the process of text classification. In particular, our method performs text classification on the encryption of embeddings from state-of-the-art models like BERT, supported by an efficient GPU implementation of CKKS encryption scheme. We show that our method offers encrypted protection of BERT embeddings, while largely preserving their utility on downstream text classification tasks.

cs.CL↗

arXiv2021

On the Scaled Inverse of $(x^i-x^j)$ modulo Cyclotomic Polynomial of the form $Φ_{p^s}(x)$ or $Φ_{p^s q^t}(x)$

The scaled inverse of a nonzero element $a(x)\in \mathbb{Z}[x]/f(x)$, where $f(x)$ is an irreducible polynomial over $\mathbb{Z}$, is the element $b(x)\in \mathbb{Z}[x]/f(x)$ such that $a(x)b(x)=c \pmod{f(x)}$ for the smallest possible positive integer scale $c$. In this paper, we investigate the scaled inverse of $(x^i-x^j)$ modulo cyclotomic polynomial of the form $Φ_{p^s}(x)$ or $Φ_{p^s q^t}(x)$, where $p, q$ are primes with $p<q$ and $s, t$ are positive integers. Our main results are that the coefficient size of the scaled inverse of $(x^i-x^j)$ is bounded by $p-1$ with the scale $p$ modulo $Φ_{p^s}(x)$, and is bounded by $q-1$ with the scale not greater than $q$ modulo $Φ_{p^s q^t}(x)$. Previously, the analogous result on cyclotomic polynomials of the form $Φ_{2^n}(x)$ gave rise to many lattice-based cryptosystems, especially, zero-knowledge proofs. Our result provides more flexible choice of cyclotomic polynomials in such cryptosystems. Along the way of proving the theorems, we also prove several properties of $\{x^k\}_{k\in\mathbb{Z}}$ in $\mathbb{Z}[x]/Φ_{pq}(x)$ which might be of independent interest.

math.NT↗

arXiv2020

HEAAN Demystified: Accelerating Fully Homomorphic Encryption Through Architecture-centric Analysis and Optimization

Homomorphic Encryption (HE) draws a significant attention as a privacy-preserving way for cloud computing because it allows computation on encrypted messages called ciphertexts. Among numerous HE schemes proposed, HE for Arithmetic of Approximate Numbers (HEAAN) is rapidly gaining popularity across a wide range of applications because it supports messages that can tolerate approximate computation with no limit on the number of arithmetic operations applicable to the corresponding ciphertexts. A critical shortcoming of HE is the high computation complexity of ciphertext arithmetic; especially, HE multiplication (HE Mul) is more than 10,000 times slower than the corresponding multiplication between unencrypted messages. This leads to a large body of HE acceleration studies, including ones exploiting FPGAs; however, those did not conduct a rigorous analysis of computational complexity and data access patterns of HE Mul. Moreover, the proposals mostly focused on designs with small parameter sizes, making it difficult to accurately estimate their performance in conducting a series of complex arithmetic operations. In this paper, we first describe how HE Mul of HEAAN is performed in a manner friendly to computer architects. Then we conduct a disciplined analysis on its computational and memory access characteristics, through which we (1) extract parallelism in the key functions composing HE Mul and (2) demonstrate how to effectively map the parallelism to the popular parallel processing platforms, multicore CPUs and GPUs, by applying a series of optimization techniques such as transposing matrices and pinning data to threads. This leads to the performance improvement of HE Mul on a CPU and a GPU by 42.9x and 134.1x, respectively, over the single-thread reference HEAAN running on a CPU. The conducted analysis and optimization would set a new foundation for future HE acceleration research.

cs.DC↗