SALSA：利用 Transformer 攻击格密码学
SALSA: Attacking Lattice Cryptography with Transformers
AI总结：
本文提出 SALSA，通过训练 Transformer 执行模运算并结合统计密码分析，对基于 LWE 的格密码方案实施机器学习攻击，可恢复中小型稀疏二元秘密实例。
摘要：
当前部署的公钥密码系统将容易受到全尺寸量子计算机的攻击。因此，“抗量子”密码系统需求很高，而基于被称为带误差学习（LWE）的困难问题的格基密码系统，已成为标准化的有力候选者。在本工作中，我们训练 Transformer 执行模运算，并将半训练模型与统计密码分析技术相结合，提出 SALSA：一种针对基于 LWE 的密码方案的机器学习攻击。SALSA 能够针对具有稀疏二元秘密的中小型 LWE 实例完全恢复秘密，并可能扩展到攻击现实世界中基于 LWE 的密码系统。
英文摘要：
Currently deployed public-key cryptosystems will be vulnerable to attacks by full-scale quantum computers. Consequently, "quantum resistant" cryptosystems are in high demand, and lattice-based cryptosystems, based on a hard problem known as Learning With Errors (LWE), have emerged as strong contenders for standardization. In this work, we train transformers to perform modular arithmetic and combine half-trained models with statistical cryptanalysis techniques to propose SALSA: a machine learning attack on LWE-based cryptographic schemes. SALSA can fully recover secrets for small-to-mid size LWE instances with sparse binary secrets, and may scale to attack real-world LWE-based cryptosystems.
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。
