Salsa Fresca：面向基于机器学习的错误学习攻击的角度嵌入与预训练
Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors
AI总结：
本研究针对现有机器学习攻击LWE问题存在的样本需求大、耗时长的问题，提出优化预处理、角度嵌入和模型预训练三种方法，大幅提升攻击效率，首次实现对n=1024维稀疏二进制密钥的ML攻击恢复。
摘要：
错误学习（LWE）是一类难解数学问题，是近期标准化的后量子密码（PQC）密钥交换与数字签名系统的底层基础。已有研究提出了针对小尺寸、稀疏密钥LWE问题的新型机器学习（ML）攻击方法，但这类攻击需要数百万个LWE样本用于训练，且恢复密钥需耗时数天。我们提出三项核心方法——更优的预处理、角度嵌入以及模型预训练——来改进这类攻击，将预处理速度提升25倍，并将模型样本效率提高10倍。我们首次证明预训练能够优化针对LWE的ML攻击并降低其成本。我们的架构改进使得攻击可扩展至更高维度的LWE问题：本研究是首个通过ML攻击恢复维度n=1024的稀疏二进制密钥的实例，该维度是采用稀疏二进制密钥的LWE同态加密应用实际使用的最小维度。
英文摘要：
Learning with Errors (LWE) is a hard math problem underlying recently standardized post-quantum cryptography (PQC) systems for key exchange and digital signatures. Prior work proposed new machine learning (ML)-based attacks on LWE problems with small, sparse secrets, but these attacks require millions of LWE samples to train on and take days to recover secrets. We propose three key methods -- better preprocessing, angular embeddings and model pre-training -- to improve these attacks, speeding up preprocessing by $25\times$ and improving model sample efficiency by $10\times$. We demonstrate for the first time that pre-training improves and reduces the cost of ML attacks on LWE. Our architecture improvements enable scaling to larger-dimension LWE problems: this work is the first instance of ML attacks recovering sparse binary secrets in dimension $n=1024$, the smallest dimension used in practice for homomorphic encryption applications of LWE where sparse binary secrets are proposed.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
