Search

Machine-Learning-as-a-Service has become increasingly popular, with Recommendation-as-a-Service as one of the representative examples. In such services, providing privacy protection for the users is an important topic. Reviewing privacy-preserving solutions which were proposed in the past decade, privacy and machine learning are often seen as two competing goals at stake. Though improving cryptographic primitives (e.g., secure multi-party computation (SMC) or homomorphic encryption (HE)) or devising sophisticated secure protocols has made a remarkable achievement, but in conjunction with state-of-the-art recommender systems often yields far-from-practical solutions. We tackle this problem from the direction of machine learning. We aim to design crypto-friendly recommendation algorithms, thus to obtain efficient solutions by directly using existing cryptographic tools. In particular, we propose an HE-friendly recommender system, refer to as CryptoRec, which (1) decouples user features from latent feature space, avoiding training the recommendation model on encrypted data; (2) only relies on addition and multiplication operations, making the model straightforwardly compatible with HE schemes. The properties turn recommendation-computations into a simple matrix-multiplication operation. To further improve efficiency, we introduce a sparse-quantization-reuse method which reduces the recommendation-computation time by $9\times$ (compared to using CryptoRec directly), without compromising the accuracy. We demonstrate the efficiency and accuracy of CryptoRec on three real-world datasets. CryptoRec allows a server to estimate a user's preferences on thousands of items within a few seconds on a single PC, with the user's data homomorphically encrypted, while its prediction accuracy is still competitive with state-of-the-art recommender systems computing over clear data. Our solution enables Recommendation-as-a-Service on large datasets in a nearly real-time (seconds) level.

Functional encryption (FE) allows an authority to issue tokens associated with various functions, allowing the holder of some token for function f to learn only \(f(\mathsf {D})\) from a ciphertext that encrypts \(\mathsf {D}\). The standard approach is to model f as a circuit, which yields inefficient evaluations over large inputs. Here, we propose a new primitive that we call updatable functional encryption (UFE), where instead of circuits we deal with RAM programs, which are closer to how programs are expressed in von Neumann architecture. We impose strict efficiency constrains in that the run-time of a token \(\mathsf {\overline{P}}\) on ciphertext \(\mathsf {CT}\) is proportional to the run-time of its clear-form counterpart (program \(\mathsf {P}\) on memory \(\mathsf {D}\)) up to a polylogarithmic factor in the size of \(\mathsf {D}\), and we envision tokens that are capable to update the ciphertext, over which other tokens can be subsequently executed. We define a security notion for our primitive and propose a candidate construction from obfuscation, which serves as a starting point towards the realization of other schemes and contributes to the study on how to compute RAM programs over public-key encrypted data.

International audience; Private functional encryption guarantees that not only the information in ciphertexts is hidden but also the circuits in decryption tokens are protected. A notable use case of this notion is query privacy in searchable encryption. Prior privacy models in the literature were fine-tuned for specific functionalities (namely, identity-based encryption and inner-product encryption), did not model correlations between ciphertexts and decryption tokens, or fell under strong uninstantiability results. We develop a new indistinguishability-based privacy notion that overcomes these limitations and give constructions supporting different circuit classes and meeting varying degrees of security. Obfuscation is a common building block that these constructions share, albeit the obfuscators necessary for each construction are based on different assumptions. Our feasibility results go beyond previous constructions in a number of ways. In particular, a keyword search scheme that we base on point obfuscators tolerates arbitrary and possibly low-entropy correlations between encrypted data and queried keywords, even under (mildly restricted) adaptive token-extraction queries. Our more elaborate keyword search scheme achieves the strongest notion of privacy that we put forth (with no restrictions), but relies on stronger forms of obfuscation. We also develop a composable and distributionally secure hyperplane membership obfuscator and use it to build an inner-product encryption scheme that achieves an unprecedented level of privacy. This, in particular, positively answers a question left open by Boneh, Raghunathan and Segev (ASIACRYPT 2013) concerning the extension and realization of enhanced security for schemes supporting this functionality.

Asymmetric searchable encryption allows searches to be carried over ciphertexts, through delegation, and by means of trapdoors issued by the owner of the data. Public Key Encryption with Keyword Search (PEKS) is a primitive with such functionality that provides delegation of exact-match searches. As it is important that ciphertexts preserve data privacy, it is also important that trapdoors do not expose the user’s search criteria. The difficulty of formalizing a security model for trapdoor privacy lies in the verification functionality, which gives the adversary the power of verifying if a trapdoor encodes a particular keyword. In this paper, we provide a broader view on what can be achieved regarding trapdoor privacy in asymmetric searchable encryption schemes, and bridge the gap between previous definitions, which give limited privacy guarantees in practice against search patterns. Since it is well-known that PEKS schemes can be trivially constructed from any Anonymous IBE scheme, we propose the security notion of Key Unlinkability for IBE, which leads to strong guarantees of trapdoor privacy in PEKS, and we construct a scheme that achieves this security notion.

Lecture Notes in Computer Science, 7341, We extend the work of Bellare, Boldyreva and Staddon on the systematic analysis of randomness reuse to construct multi-recipient encryption schemes to the case where randomness is reused across different cryptographic primitives. We find that through the additional binding introduced through randomness reuse, one can actually obtain a security amplification with respect to the standard black-box compositions, and achieve a stronger level of security. We introduce stronger notions of security for encryption and signatures, where challenge messages can depend in a restricted way on the random coins used in encryption, and show that two variants of the KEM/DEM paradigm give rise to encryption schemes that meet this enhanced notion of security. We obtain the most efficient signcryption scheme to date that is secure against insider attackers without random oracles., (undefined)