mlsanityData to 7 Oct 2026

secureTF: A Secure TensorFlow Framework

arXiv 2101.08204 ↗First posted 20 Jan 2021cs.CR cs.DC cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

Data-driven intelligent applications in modern online services have become ubiquitous. These applications are usually hosted in the untrusted cloud computing infrastructure. This poses significant security risks since these applications rely on applying machine learning algorithms on large datasets which may contain private and sensitive information. To tackle this challenge, we designed secureTF, a distributed secure machine learning framework based on Tensorflow for the untrusted cloud infrastructure. secureTF is a generic platform to support unmodified TensorFlow applications, while providing end-to-end security for the input data, ML model, and application code. secureTF is built from ground-up based on the security properties provided by Trusted Execution Environments (TEEs). However, it extends the trust of a volatile memory region (or secure enclave) provided by the single node TEE to secure a distributed infrastructure required for supporting unmodified stateful machine learning applications running in the cloud. The paper reports on our experiences about the system design choices and the system deployment in production use-cases. We conclude with the lessons learned based on the limitations of our commercially available platform, and discuss open research problems for the future work.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 24 of its 99 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

24 of 99 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2016Deep Learning with Differential Privacycited by 2,682
  6. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  7. 2015Empirical Evaluation of Rectified Activations in Convolutional Networkcited by 515
  8. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  9. 2018Gazelle: A Low Latency Framework for Secure Neural Network Inferencecited by 193
  10. 2018Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardwarecited by 101
  11. 2019CrypTFlow: Secure TensorFlow Inferencecited by 61
  12. 2018Spectre Attacks: Exploiting Speculative Executioncited by 47
12 more
  1. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  2. 2017A Brief Introduction to Machine Learning for Engineerscited by 20
  3. 2017Leaky Cauldron on the Dark Land: Understanding Memory Side-Channel Hazards in SGXcited by 15
  4. 2017Software Grand Exposure: SGX Cache Attacks Are Practicalcited by 14
  5. 2018SgxPectre Attacks: Stealing Intel Secrets from SGX Enclaves via Speculative Executioncited by 13
  6. 2019TensorSCONE: A Secure TensorFlow Framework using Intel SGXcited by 8
  7. 2020Trust Management as a Service: Enabling Trusted Execution in the Face of Byzantine Stakeholderscited by 5
  8. 2018CYCLOSA: Decentralizing Private Web Search Through SGX-Based Browser Extensionscited by 2
  9. 2020TEEMon: A continuous performance monitoring framework for TEEscited by 2
  10. 2021A practical approach for updating an integrity-enforced operating systemcited by 2
  11. 2017Slick: Secure Middleboxes using Shielded Executioncited by 1
  12. 2021T-Lease: A Trusted Lease Primitive for Distributed Systemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 1; 2023: 2; 2024: 3; 2025: 0; 2026: 1.

12 papers.

  1. 2021Secure Quantized Training for Deep Learningcited by 15
  2. 2021Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGXcited by 14
  3. 2023A Survey of Secure Computation Using Trusted Execution Environmentscited by 8
  4. 2021Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspectivecited by 4
  5. 2026Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AIcited by 3
  6. 2021Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Supportcited by 2
  7. 2021Plinius: Secure and Persistent Machine Learning Model Trainingcited by 2
  8. 2022Local Model Reconstruction Attacks in Federated Learning and their Usescited by 2
  9. 2023Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigationscited by 1
  10. 2024VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devicescited by 1
  11. 2024Attribute Inference Attacks for Federated Regression Taskscited by 1
  12. 2024Protecting Confidentiality, Privacy and Integrity in Collaborative Learningcited by 0