SALSA VERDE: a machine learning attack on Learning With Errors with sparse small secrets

被引:0
|
作者
Li, Cathy Yuanchen [1 ,2 ]
Wenger, Emily [3 ]
Allen-Zhu, Zeyuan [1 ,2 ]
Charton, Francois [1 ,2 ]
Lauter, Kristin [1 ,2 ]
机构
[1] FAIR, Chicago, IL 60637 USA
[2] Meta, Seattle, WA 98101 USA
[3] Univ Chicago, Chicago, IL USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Learning with Errors (LWE) is a hard math problem used in post-quantum cryptography. Homomorphic Encryption (HE) schemes rely on the hardness of the LWE problem for their security, and two LWE-based cryptosystems were recently standardized by NIST for digital signatures and key exchange (KEM). Thus, it is critical to continue assessing the security of LWE and specific parameter choices. For example, HE uses secrets with small entries, and the HE community has considered standardizing small sparse secrets to improve efficiency and functionality. However, prior work, SALSA and PICANTE, showed that ML attacks can recover sparse binary secrets. Building on these, we propose VERDE, an improved ML attack that can recover sparse binary, ternary, and narrow Gaussian secrets. Using improved preprocessing and secret recovery techniques, VERDE can attack LWE with larger dimensions (n = 512) and smaller moduli (log(2) q = 12 for n = 256), using less time and power. We propose novel architectures for scaling. Finally, we develop a theory that explains the success of ML LWE attacks.
引用
收藏
页数:19
相关论文
共 50 条
  • [41] Machine learning techniques for ocular errors analysis
    Libralao, GL
    de Almeida, OCP
    Netto, AV
    Delbem, ACB
    de Carvalho, ACPLF
    MACHINE LEARNING FOR SIGNAL PROCESSING XIV, 2004, : 569 - 578
  • [42] BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning
    Cui, Jing
    Han, Yufei
    Ma, Yuzhe
    Jiao, Jianbin
    Zhang, Junge
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 10, 2024, : 11687 - 11694
  • [43] Sparse Black-Box Video Attack with Reinforcement Learning
    Xingxing Wei
    Huanqian Yan
    Bo Li
    International Journal of Computer Vision, 2022, 130 : 1459 - 1473
  • [44] Sparse Black-Box Video Attack with Reinforcement Learning
    Wei, Xingxing
    Yan, Huanqian
    Li, Bo
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (06) : 1459 - 1473
  • [45] A Survey on Attack Detection Methods For IOT Using Machine Learning And Deep Learning
    Babu, Meenigi Ramesh
    Veena, K. N.
    ICSPC'21: 2021 3RD INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING AND COMMUNICATION (ICPSC), 2021, : 625 - 630
  • [46] Online ADMM-Based Extreme Learning Machine for Sparse Supervised Learning
    Song, Tianheng
    Li, Dazi
    Liu, Zhiyin
    Yang, Weimin
    IEEE ACCESS, 2019, 7 : 64533 - 64544
  • [47] GIOPHANTUS DISTINGUISHING ATTACK IS A LOW DIMENSIONAL LEARNING WITH ERRORS PROBLEM
    Ding, Jintai
    Deaton, Joshua
    Schmidt, Kurt
    ADVANCES IN MATHEMATICS OF COMMUNICATIONS, 2020, 14 (04) : 573 - 577
  • [48] GIOPHANTUS DISTINGUISHING ATTACK IS A LOW DIMENSIONAL LEARNING WITH ERRORS PROBLEM
    Ding, Jintai
    Deaton, Joshua
    Schmidt, Kurt
    ADVANCES IN MATHEMATICS OF COMMUNICATIONS, 2020, 14 (01) : 171 - 175
  • [49] Cloud Insider Attack Detection Using Machine Learning
    Nathezhtha, T.
    Vaidehi, V.
    PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ADVANCED COMPUTING (ICRTAC-CPS 2018), 2018, : 60 - 65
  • [50] Detection of DDoS Attack in IoT Using Machine Learning
    Kumar, Naveen
    Aleem, Abdul
    Kumar, Sachin
    ADVANCED NETWORK TECHNOLOGIES AND INTELLIGENT COMPUTING, ANTIC 2021, 2022, 1534 : 190 - 199