ON DATA BANKS AND PRIVACY HOMOMORPHISMS

By Ronald L. Rivest, M. Dertouzos. 1978

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Privacy & Security

Citations in the corpus

Backdoor attacks and defenses in feature-partitioned collaborative learning (2020, background): “Privacy-preserving techniques such as Homomorphic Encryption (HE) (Rivest et al., 1978; Acar et al., 2018), Secure Multi-party Computation (SMPC) (Yao, 1982) and Differential Privacy (DP) (Dwork, 2006) are typically applied in these frameworks to preserve user privacy and data confidentiality.”
Federated Machine Learning (2019, background): “d a differential privacy approach to federated learning in order to add protection to client-side data by hiding client’s contributions during training. Homomorphic Encryption. Homomorphic Encryption [53] is also adopted to protect user data privacy through parameter exchange under the encryption me”
Crypto-Nets: Neural Networks over Encrypted Data (2014, methodology): “A Homomorphic Encryption (HE) scheme (Rivest et al., 1978) preserves some structure of the original message space.”
SoK: Security and Privacy in Machine Learning (2018, methodology): “use homomorphic encryption [97] to encrypt the data in a form that allows a neural network to process it without decrypting it [98].”
Gazelle: A Low Latency Framework for Secure Neural Network Inference (2018, methodology): “Homomorphic Encryption: Fully Homomorphic Encryption, or FHE, is an encryption method that allows anyone to compute an arbitrary function f on an encryption of x , without decrypting it and without knowledge of the private key [5], [14], [31].”
A Survey on Homomorphic Encryption Schemes (2017, methodology): “There are several useful PHE examples [Rivest et al. 1978b; Goldwasser and Mi-cali 1982; ElGamal 1985; Benaloh 1994; Naccache and Stern 1998; Okamoto and Uchiyama 1998; Paillier 1999; Damgård and Jurik 2001; Kawachi et al. 2007] in the literature.”
Algorithms in HElib (2014, background): “Homomorphic encryption (HE) [18, 8] enables performing arithmetic operations on encrypted data even without knowing the secret decryption key.”
A Communication Efficient Collaborative Learning Framework for Distributed Features (2019, methodology): “In addition, to prevent data leakage, privacypreserving techniques, such as Homomorphic Encryption (HE) [11], Secure Multi-party Computation (SMPC) [12] are typically applied to transmitted data [4, 10, 9], adding expensive communication overhead to the architectures.”
Cryptanalysis of a homomorphic encryption scheme from ISIT 2008 (2012, background): “Key words: Lattice-based, Homomorphic encryption, Keyrecovery attack I. INTRODUCTION Homomorphic encryption is an interesting concept to protect privacy, which was proposed by Rivest, Adleman and Dertouzos [26] in 1978.”
Encrypted statistical machine learning: new privacy preserving methods (2015, background): “Rivest et al. (1978) initially showed that it may be possible to design an encryption scheme that supports restricted mathematical computations without decrypting.”