BlindexTEE: A Blind Index Approach towards TEE-supported End-to-end Encrypted DBMS

• URL: http://arxiv.org/abs/2411.02084v1
• Date: Mon, 04 Nov 2024 13:45:28 GMT
• Title: BlindexTEE: A Blind Index Approach towards TEE-supported End-to-end Encrypted DBMS
• Abstract summary: We present BlindexTEE, a new component that sits between the application business-logic and the database. BlindexTEE is shielded from malicious users or compromised environments by executing inside an SEV-SNP confidential VM. By encrypting and re-encrypting data, it builds blind indices, used later on to efficiently query the indices.
• Score: 1.7856481599200345
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Using cloud-based applications comes with privacy implications, as the end-user looses control over their data. While encrypting all data on the client is possible, it largely reduces the usefulness of database management systems (DBMS) that are typically built to efficiently query large quantities of data. We present BlindexTEE, a new component that sits between the application business-logic and the database. BlindexTEE is shielded from malicious users or compromised environments by executing inside an SEV-SNP confidential VM, AMD's trusted execution environment (TEE). BlindexTEE is in charge of end-to-end encryption of user data while preserving the ability of the DBMS to efficiently filter data. By decrypting and re-encrypting data, it builds blind indices, used later on to efficiently query the DBMS. We demonstrate the practicality of BlindexTEE with MySQL in several micro- and macro-benchmarks, achieving overheads between 36.1% and 462% over direct database access depending on the usage scenario.

Related papers

• Confidential Databases Without Cryptographic Mappings [5.019292555403337]
  FEDB is a novel CDB design that removes cryptographic operations from the critical path.<n>This paradigm shift reduces the runtime overhead by up to 78.0 times on industry-standard benchmarks.
  arXiv  Detail & Related papers  (2026-03-19T12:37:35Z)
• FHE-SQL: Fully Homomorphic Encrypted SQL Database [0.09176056742068811]
  FHE- is a privacy-preserving database system that enables secure query processing on encrypted data.<n>Unlike property-preserving systems such as CryptDB, FHE- performs computations entirely under encryption.
  arXiv  Detail & Related papers  (2025-10-17T08:07:27Z)
• MAGPIE: A dataset for Multi-AGent contextual PrIvacy Evaluation [54.410825977390274]
  Existing benchmarks to evaluate contextual privacy in LLM-agents primarily assess single-turn, low-complexity tasks.<n>We first present a benchmark - MAGPIE comprising 158 real-life high-stakes scenarios across 15 domains.<n>We then evaluate the current state-of-the-art LLMs on their understanding of contextually private data and their ability to collaborate without violating user privacy.
  arXiv  Detail & Related papers  (2025-06-25T18:04:25Z)
• WikiDBGraph: A Data Management Benchmark Suite for Collaborative Learning over Database Silos [48.88393315169039]
  Collaborative learning (CL) techniques enable multiple parties to train models jointly without sharing raw data.<n>Current CL benchmarks and algorithms primarily target the learning step under assumptions of isolated, aligned, and joinable databases.<n>We build a large-scale dataset constructed from 100,000 real-world relational databases linked by 17 million weighted edges.
  arXiv  Detail & Related papers  (2025-05-22T13:07:06Z)
• Differentially Private Learned Indexes [4.290415158471898]
  We address the problem of efficiently answering predicate queries on encrypted databases, those secured by Trusted Execution Environments (TEEs) A common strategy in modern databases to accelerate predicate queries is the use of indexes, which map attribute values (keys) to their corresponding positions in a sorted data array. Unfortunately, indexes cannot be directly applied to encrypted databases due to strong data dependent leakages. We propose leveraging learned indexes, a trending technique that repurposes machine learning models as indexing structures, to build more compact DP indexes.
  arXiv  Detail & Related papers  (2024-10-28T16:04:58Z)
• Relational Database Augmented Large Language Model [59.38841050766026]
  Large language models (LLMs) excel in many natural language processing (NLP) tasks. They can only incorporate new knowledge through training or supervised fine-tuning processes. This precise, up-to-date, and private information is typically stored in relational databases.
  arXiv  Detail & Related papers  (2024-07-21T06:19:10Z)
• Robust Utility-Preserving Text Anonymization Based on Large Language Models [80.5266278002083]
  Text anonymization is crucial for sharing sensitive data while maintaining privacy. Existing techniques face the emerging challenges of re-identification attack ability of Large Language Models. This paper proposes a framework composed of three LLM-based components -- a privacy evaluator, a utility evaluator, and an optimization component.
  arXiv  Detail & Related papers  (2024-07-16T14:28:56Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• Privacy-Enhanced Database Synthesis for Benchmark Publishing [16.807486872855534]
  Differential privacy has become a key method for safeguarding privacy when sharing data, but the focus has largely been on minimizing errors in aggregate queries or classification tasks. This paper delves into the creation of privacy-preserving databases specifically for benchmarking, aiming to produce a differentially private database. PrivBench uses sum-product networks (SPNs) to partition and sample data, enhancing data representation while securing privacy.
  arXiv  Detail & Related papers  (2024-05-02T14:20:24Z)
• Enc2DB: A Hybrid and Adaptive Encrypted Query Processing Framework [47.11111145443189]
  We introduce Enc2DB, a novel secure database system following a hybrid strategy on and openGauss. We present a micro-benchmarking test and self-adaptive mode switch strategy that can choose the best execution path (cryptography or TEE) to answer a given query. We also design and implement a ciphertext index compatible with native cost model and querys to accelerate query processing.
  arXiv  Detail & Related papers  (2024-04-10T08:11:12Z)
• Privacy-Preserved Neural Graph Databases [48.57788773216699]
  We propose a privacy-preserved neural graph database (P-NGDB) framework to alleviate the risks of privacy leakage in NGDBs. We introduce adversarial training techniques in the training stage to enforce the NGDBs to generate indistinguishable answers when queried with private information.
  arXiv  Detail & Related papers  (2023-12-25T02:32:05Z)
• DiCE -- A Data Encryption Proxy for the Cloud [0.0]
  There are concerns about the confidentiality and security of the outsourced data. The DiCE' driver parses queries as a proxy and encrypts these queries. This allows to execute many queries on an encrypted database in the cloud with the relational performance as on unencrypted databases.
  arXiv  Detail & Related papers  (2023-10-09T13:33:59Z)
• Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs [89.68522473384522]
  We present Bird, a big benchmark for large-scale database grounded in text-to-efficient tasks. Our emphasis on database values highlights the new challenges of dirty database contents. Even the most effective text-to-efficient models, i.e. ChatGPT, achieves only 40.08% in execution accuracy.
  arXiv  Detail & Related papers  (2023-05-04T19:02:29Z)
• A Quantum-based Database Query Scheme for Privacy Preservation in Cloud Environment [7.331387596311974]
  Privacy-preserving database query allows the user to retrieve a data item from the cloud database without revealing the information of the queried data item. All the data items of the database are encrypted by different keys for protecting server's privacy. Two oracle operations, a modified Grover iteration, and a special offset encryption mechanism are combined together to ensure that the client can correctly query the desirable data item.
  arXiv  Detail & Related papers  (2020-02-01T11:14:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.