This work proposes a multi-level compiler framework to transform programs with loop structures to efficient algorithms over fully homomorphic encryption (FHE). We observe that, when loops operate over ciphertexts, it becomes extremely challenging to effectively interpret the control structures within the loop and construct operator cost models for the main body of the loop. Consequently, most existing compiler frameworks have inadequate support for programs involving non-trivial loops, undermining the expressiveness of programming over FHE. To achieve both efficient and general program execution over FHE, we propose CHLOE, a new compiler framework with multi-level control-flow analysis for the effective optimization of compound repetition control structures. We observe that loops over FHE can be classified into two categories depending on whether the loop condition is encrypted, namely, the transparent loops and the oblivious loops. For transparent loops, we can directly inspect the control structures and build operator cost models to apply FHE-specific loop segmentation and vectorization in a fine-grained manner. Meanwhile, for oblivious loops, we derive closed-form expressions and static analysis techniques to reduce the number of potential loop paths and conditional branches. In the experiment, we show that CHLOE can compile programs with complex loop structures into efficient executable codes over FHE, where the performance improvement ranges from 1.5× to 54× (up to 105× for programs containing oblivious loops) when compared to programs produced by the-state-of-the-art FHE compilers.

Fully homomorphic encryption (FHE) based database outsourcing is drawing growing research interests. At its current state, there exist two primary obstacles against FHE-based encrypted databases (EDBs): i) low data precision, and ii) high computational latency. To tackle the precision-performance dilemma, we introduce ArcEDB, a novel FHE-based SQL evaluation infrastructure that simultaneously achieves high data precision and fast query evaluation. Based on a set of new plaintext encoding schemes, we are able to execute arbitrary-precision ciphertext-to-ciphertext homomorphic comparison orders of magnitude faster than existing methods. Meanwhile, we propose efficient conversion algorithms between the encoding schemes to support highly composite SQL statements, including advanced filter-aggregation and multi-column synchronized sorting. We perform comprehensive experiments to study the performance characteristics of ArcEDB. In particular, we show that ArcEDB can be up to 57× faster in homomorphic filtering and up to 20× faster over end-to-end SQL queries when compared to the state-of-the-art FHE-based EDB solutions. Using ArcEDB, a SQL query over a 10K-row time-series EDB with 64-bit timestamps only runs for under one minute.

With the rapid advancements in machine learning and the widespread adoption of Model-as-a-Service (MaaS) platforms, there has been significant attention on convolutional neural network (CNN) inference services. However, traditional inference services over plaintext data and models are susceptible to the risks of data and model leakage. Although several privacy-preserving CNN inference schemes utilizing trusted execution environment (TEE) and cryptography have been proposed, their security models and performance still have limitations in some scenarios. Aiming at the above challenges, we present an oblivious neural network prediction scheme with semi-honest TEE, namely ToNN, which ensures the security of users’ inputs, outputs, and the model itself. Specifically, based on the limited memory of the TEE, we design secure protocols to perform CNN calculations securely and efficiently, which are friendly to support the single instruction multiple data technique. Additionally, we propose a look-up-table method to optimize the convolution and pooling layers calculations. A detailed security analysis under the simulation-based real/ideal worlds model shows that ToNN can achieve the desired security. Extensive simulation results further demonstrate that ToNN can improve the performance of linear calculations by$\textbf {4.86}\times $and non-linear calculation by$\textbf {37.68}\times $, and can be implemented effectively with low computation and communication costs.

CRYSTALS-Kyber, as the only public key encryption (PKE) algorithm selected by the National Institute of Standards and Technology (NIST) in the third round, is considered one of the most promising post-quantum cryptography (PQC) schemes. Lattice-based cryptography uses complex discrete algorithm problems on lattices to build secure encryption and decryption systems to resist attacks from quantum computing. Performance is an important bottleneck affecting the promotion of post quantum cryptography. In this paper, we present a High-performance Implementation of Kyber (named HI-Kyber) on the NVIDIA GPUs, which can increase the key-exchange performance of Kyber to the million-level. Firstly, we propose a lattice-based PQC implementation architecture based on kernel fusion, which can avoid redundant global-memory access operations. Secondly, We optimize and implement the core operations of CRYSTALS-Kyber, including Number Theoretic Transform (NTT), inverse NTT (INTT), pointwise multiplication, etc. Especially for the calculation bottleneck NTT operation, three novel methods are proposed to explore extreme performance: the sliced layer merging (SLM), the sliced depth-first search (SDFS-NTT) and the entire depth-first search (EDFS-NTT), which achieve a speedup of 7.5%, 28.5%, and 41.6% compared to the native implementation. Thirdly, we conduct comprehensive performance experiments with different parallel dimensions based on the above optimization. Finally, our key exchange performance reaches 1,664 kops/s. Specifically, based on the same platform, our HI-Kyber is 3.52× that of the GPU implementation based on the same instruction set and 1.78× that of the state-of-the-art one based on AI-accelerated tensor core.

Online medical primary diagnosis system, which can provide convenient medical decision support through applying mobile communication and data analysis technology, has been considered as a promising approach to improve the quality of healthcare service. However, it still faces many severe challenges on the privacy of users' health information and the accuracy of diagnosis result, which deter the wide adoption of online medical primary diagnosis system. In this paper, we propose an efficient and privacy-preserving online medical primary diagnosis (CINEMA) framework. Within CINEMA framework, users can access online medical primary diagnosing service accurately without divulging their medical data. Specifically, based on fast secure permutation and comparison technique, the encrypted user's query is directly operated at the service provider (SP) without decryption, and the diagnosis result can only be decrypted by the user, meanwhile, the diagnosis model in SP can also be protected. Through extensive analysis, we show that CINEMA can ensure that user's health information and healthcare SP's diagnosis model are kept confidential, and has significantly reduce computation and communication overhead. In addition, performance evaluations via implementing CINEMA demonstrate its effectiveness in term of the real environment.

Friend discovery has been one of the hot topics in our social activities over the past decade. Mobile users have more opportunities to discover and make new social interactions with others in vicinity to build and extend their social communities. However, the inevitable information releasing conflicts with the increasing privacy concerns. In this paper, we employ the concept of friend-of-friend and design a secure and accurate friend discovery for privacy-aware mobile users in Proximity-based Mobile Social Networks (PMSNs). We first construct a novel similarity function with fully considering the number of common attributes, the corresponding priorities and the ratio of matched attributes over all the inputs. Then we develop a secure friend recommendation phase based on a carefully combination of the commutative encryption function and the bilinear pairings. The security and performance are thoroughly analyzed and evaluated via detailed simulations.

Privacy issues in group matching problem have become one of the most important things in Mobile Social Networks (MSNs) currently. Mobile users may feel uncomfortable when releasing personal information to some irrelevant people or groups. In this paper, we propose a practical group matching scheme without employing any Trusted Third Party (TTP) for privacy-aware users in MSNs. We first propose a fuzzy matrix algorithm to generate user's authority instead of complex cryptographic computations to reduce the communication and computation overhead, and thus build a public set to store all the group members' profiles and authorities. As a result, our group matching does not need all the group members are online anymore. Moreover, we utilize the Ochiai similarity considering both of the number of common attributes and the size of each user's profile. The privacy and performance are analyzed and evaluated via detailed simulations.