Fully Homomorphic Encryption (FHE) has emerged as one of the key technologies for privacy-preserving computation, enabling arbitrary computation directly on encrypted data. Vectorized FHE schemes, such as Brakerski/Fan--Vercauteren (BFV), Brakerski--Gentry--Vaikuntanathan (BGV), and Cheon--Kim--Kim--Song (CKKS), are typically used in applications dealing with large datasets, for example, confidential database queries and private ML inference. These FHE schemes are based on the computational...

FAEST is a symmetric-key post-quantum digital signature scheme and a third-round candidate in the NIST Additional Digital Signatures standardization process. Its signing path concentrates cost in two operations: round-wise constraint generation, which proves in zero knowledge that the AES circuit is computed correctly, and finite-field multiplication, which computes the leaf nodes of a vector commitment. This paper accelerates both operations on a CUDA-enabled GPU, with AES round constraint...

Zero-knowledge proof systems are increasingly relying on the Sumcheck protocol to avoid the FFT-heavy structure of earlier SNARK designs. Sumcheck is well suited for GPU acceleration; it consists of sequential rounds where each round performs regular, parallelizable operations over large multilinear evaluation tables. The focus is on how to organize this work across rounds: intuitively, the active polynomial state should remain close to the device that processes it, the CPU-GPU boundary...

GPU Tensor Cores, specialized hardware units designed to accelerate matrix multiplication, have served as the primary engine behind the AI revolution. Given the exponential performance gains they have delivered, aligning cryptographic implementations with this hardware evolution is critical. This is particularly acute for zero-knowledge proofs (ZKPs), a cryptographic primitive that currently grapples with high proof generation costs. Existing GPU implementations for ZKPs rely exclusively on...

Although recent surveys on privacy-enhancing technologies concluded that FHE cannot feasibly evaluate non-linear activation functions in modern ML architectures, 20 CKKS-based frameworks have since demonstrated end-to-end private inference of LLMs with up to 8B parameters. However, as the field grows rapidly, the literature has become fragmented. Frameworks differ in ciphertext packing layouts, model fidelity, software and hardware stacks, and reported metrics, which hinder direct comparison...

Privacy-preserving machine learning (PPML) enables inference over sensitive data without exposing raw inputs, with CKKS being a widely adopted scheme for approximate arithmetic. However, existing CKKS implementations are primarily based on 64-bit residue number system (RNS) representations, creating a mismatch with modern GPUs optimized for 32-bit integer arithmetic. This mismatch introduces substantial computational overhead, limiting the practicality of encrypted transformer...

Hamming Quasi-Cyclic (HQC) has been selected by NIST for standardization in the post-quantum landscape. As deployment approaches, implementation security becomes as critical as mathematical hardness. In this work, we demonstrate that source-level constant-time coding is not a standalone guarantee: the compiled binary must inherently preserve this behavior. We identify a severe compiler-induced vulnerability within the official AVX2-optimized implementation of HQC, despite its claims of...

Zero-knowledge Succinct Non-interactive Arguments of Knowledge (zk-SNARKs) are cryptographic protocols that allow a prover to convince verifiers of the correctness of a statement without revealing any additional information. Recent zk-SNARK constructions have shifted from univariate to multivariate polynomial-based designs, reducing the proving complexity from quasilinear to linear by avoiding costly univariate polynomial interpolation. This shift, however, makes the sumcheck protocol—a...

Homomorphic Encryption (HE) enables secure cloud computing through computations on encrypted data, but the physical execution of HE workloads on shared GPUs can still expose relevant metadata through microarchitectural behavior. Implementation-level irregularities in key switching, rounding, and modular correction may create observable hardware footprints even when cryptographic confidentiality remains intact. We present a case study of BFV relinearization in a state-of-the-art GPU HE...

Secure TransFormer Inference (STFI) for LLMs aims to protect both user inputs and model parameters. Fully Homomorphic Encryption (FHE) offers a promising approach for STFI due to its non-interactivity, which eliminates communication overhead. However, FHE-based STFI incurs significant computational costs compared to plaintext inference. Recent advancements have accelerated inference by optimizing packing strategies and reducing the number of rotations. Despite these improvements, several...

Homomorphic Encryption (HE) provides strong data privacy for cloud services but at the cost of prohibitive computational overhead. While GPUs have emerged as a practical platform for accelerating HE, there remains an order-of-magnitude energy-efficiency gap compared to specialized (but expensive) HE ASICs. This paper explores an alternate direction: leveraging existing AI accelerators, like Google's TPUs with coarse-grained compute and memory architectures, to offer a path toward ASIC-level...

Hamming Quasi-Cyclic (HQC) was a candidate algorithm in the fourth round of the National Institute of Standards and Technology (NIST) post-quantum cryptography (PQC) standardization process and was ultimately selected as a standardized cryptographic scheme in the latest round. To date, although HQC has been optimized for FPGA, CPU, and other platforms, research on GPU-based parallel acceleration remains significantly underexplored. Given this, our research aims to investigate the feasibility...

Although the lattice-estimator predicts that Learning with Errors instances having small and very sparse secrets can be broken by hybrid attacks with modest computational resources, no efficient open-source implementation of these attacks exists. This work implements the so-called Guess + Verify attack (G+V) analysed by Albrecht et al. (SAC'19), containing three improvements: (1) cuBLASter, a GPU-based implementation of the lattice basis reduction software BLASter by Ducas et al....

Linear error-correcting codes with fast encoding and high minimum distance are a central primitive across modern cryptography. They appear prominently in at least two domains: (1) pseudorandom correlation generators (PCGs), which enable sublinear-communication generation of correlations such as oblivious transfer and vector oblivious linear evaluation, and (2) zero-knowledge proof systems, where linear-time encoders underpin proof soundness and scalability. In both settings, the prover or...

Multi-key fully homomorphic encryption (MK-FHE) enables secure computation over ciphertexts under different keys, but its practicality is hindered by inefficient bootstrapping. In this work, we propose \ours, a new MK-FHE scheme with highly efficient bootstrapping. Our bootstrapping framework improves upon the best-known complexity, reducing it from ${O}(dkn)$ to ${O}(kn)$, and further to ${O}(\sqrt{kn})$ under parallelization, where $d$ is the gadget length (typically scaling with the...

The rise of quantum computers results in many cryptographic systems being no longer considered sufficiently secure. Algorithms from the field of post-quantum cryptography promise to provide security against the new systems. However, PQC algorithms are generally more computationally intensive than classical cryptography. In order to increase suitability of PQC for everyday use, this paper investigates their acceleration using GPUs. For this purpose, we analyzed research in the field and...

This paper presents an efficient framework for private Transformer inference that combines Homomorphic Encryption (HE) and Secure Multi-party Computation (MPC) to protect data privacy. Existing methods often leverage HE for linear layers (e.g., matrix multiplications) and MPC for non-linear layers (e.g., Softmax activation functions), but the conversion between HE and MPC introduces significant communication costs. The proposed framework, dubbed BLB, overcomes this by breaking down layers...

The growing deployment of large language models (LLMs) in privacy-sensitive settings demands inference mechanisms that preserve data confidentiality. Homomorphic encryption (HE) offers a principled solution by enabling computation directly on encrypted data; however, existing solutions struggle to scale to full LLMs. We present Tricycle, a system for efficient private transformer inference. At its core, Tricycle introduces tricyclic encodings, a novel packing scheme that enables batch matrix...

Side-channel attacks are increasingly recognized as a significant threat to hardware roots of trust. As a result, cryptographic module designers must ensure that their modules are resilient to such attacks before deployment. However, efficient evaluation of side-channel vulnerabilities in cryptographic implementations remains challenging. This paper introduces an open-source framework integrating FPGA designs, power measurement tools, and high-performance side-channel analysis libraries to...

Privacy-preserving neural network inference using Fully Homomorphic Encryption (FHE) faces significant challenges in efficiently evaluating non-polynomial functions, such as activation functions, which are critical for introducing non-linearity in neural networks. Full-Domain Functional Bootstrap (FDFB) algorithms provide a promising solution by enabling the evaluation of arbitrary functions while simultaneously refreshing ciphertexts to manage noise accumulation. Despite their theoretical...

Three-party secret sharing-based computation has emerged as a promising approach for secure deep learning, benefiting from its high throughput. However, it still faces persistent challenges in computing complex operations such as secure Sign-Bit Extraction, particularly in high-latency and low-bandwidth networks. A recent work, Aegis (Lu et al., Cryptology ePrint'2023), made significant strides by proposing a constant-round DGK-style Sign-Bit Extraction protocol with GPU acceleration on...