mlsanityData to 7 Oct 2026

Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications

arXiv 1801.03239 ↗First posted 10 Jan 2018cs.CR cs.AIcited by 67

Not on the map. Why?

Abstract (arXiv)

We present Chameleon, a novel hybrid (mixed-protocol) framework for secure function evaluation (SFE) which enables two parties to jointly compute a function without disclosing their private inputs. Chameleon combines the best aspects of generic SFE protocols with the ones that are based upon additive secret sharing. In particular, the framework performs linear operations in the ring mathbbZ2l using additively secret shared values and nonlinear operations using Yao's Garbled Circuits or the Goldreich-Micali-Wigderson protocol. Chameleon departs from the common assumption of additive or linear secret sharing models where three or more parties need to communicate in the online phase: the framework allows two parties with private inputs to communicate in the online phase under the assumption of a third node generating correlated randomness in an offline phase. Almost all of the heavy cryptographic operations are precomputed in an offline phase which substantially reduces the communication overhead. Chameleon is both scalable and significantly more efficient than the ABY framework (NDSS'15) it is based on. Our framework supports signed fixed-point numbers. In particular, Chameleon's vector dot product of signed fixed-point numbers improves the efficiency of mining and classification of encrypted data for algorithms based upon heavy matrix multiplications. Our evaluation of Chameleon on a 5 layer convolutional deep neural network shows 133x and 4.2x faster executions than Microsoft CryptoNets (ICML'16) and MiniONN (CCS'17), respectively.

Key facts. Cited by 67 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 10; 2023: 12; 2024: 12; 2025: 8; 2026: 5.

67 papers.

Sort:

By area:

  1. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  2. 2022MPCFormer: fast, performant and private Transformer inference with MPCcited by 67
  3. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  4. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  5. 2021SIRNN: A Math Library for Secure RNN Inferencecited by 28
  6. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  7. 2021LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Visioncited by 20
  8. 2021Secure Quantized Training for Deep Learningcited by 15
  9. 2021Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learningcited by 14
  10. 2021Privacy-Preserving Feature Selection with Secure Multiparty Computationcited by 12
  11. 2022Autonomy and Intelligence in the Computing Continuum: Challenges, Enablers, and Future Directions for Orchestrationcited by 12
  12. 2024TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deploymentcited by 11
38 more
  1. 2021Privacy-Preserving Video Classification with Convolutional Neural Networkscited by 10
  2. 2024A Survey on Intelligent Internet of Things: Applications, Security, Privacy, and Future Directionscited by 10
  3. 2021PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Settingcited by 9
  4. 2022SecureFedYJ: a safe feature Gaussianization protocol for Federated Learningcited by 9
  5. 2023East: Efficient and Accurate Secure Transformer Framework for Inferencecited by 9
  6. 2021Tetrad: Actively Secure 4PC for Secure Training and Inferencecited by 8
  7. 2022Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representationscited by 7
  8. 2021SAFELearning: Enable Backdoor Detectability In Federated Learning With Secure Aggregationcited by 5
  9. 2021Towards Secure and Practical Machine Learning via Secret Sharing and Random Permutationcited by 5
  10. 2022Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)cited by 5
  11. 2023QuMoS: A Framework for Preserving Security of Quantum Machine Learning Modelcited by 5
  12. 2023Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryptioncited by 5
  13. 2023Attesting Distributional Properties of Training Data for Machine Learningcited by 5
  14. 2024PristiQ: A Co-Design Framework for Preserving Data Security of Quantum Learning in the Cloudcited by 5
  15. 2024State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Surveycited by 5
  16. 2024MPC-Minimized Secure LLM Inferencecited by 5
  17. 2021Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Surveycited by 4
  18. 2021Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimationcited by 4
  19. 2022SCOTCH: An Efficient Secure Computation Framework for Secure Aggregationcited by 4
  20. 2022Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanismscited by 4
  21. 2022MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inferencecited by 4
  22. 2021Reducing ReLU Count for Privacy-Preserving CNN Speedupcited by 3
  23. 2025Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsitycited by 3
  24. 2021Fast Privacy-Preserving Text Classification based on Secure Multiparty Computationcited by 2
  25. 2023Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuitscited by 2
  26. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  27. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  28. 2026AgenTEE: Confidential LLM Agent Execution on Edge Devicescited by 2
  29. 2026Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddingscited by 2
  30. 2021S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Trainingcited by 1
  31. 2021Efficient Encrypted Inference on Ensembles of Decision Treescited by 1
  32. 2022MPClan: Protocol Suite for Privacy-Conscious Computationscited by 1
  33. 2023Securing Neural Networks with Knapsack Optimizationcited by 1
  34. 2023Compact: Approximating Complex Activation Functions for Secure Computationcited by 1
  35. 2023Privacy Preserving Multi-Agent Reinforcement Learning in Supply Chainscited by 1
  36. 2024Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumptioncited by 1
  37. 2024VeriSplit: Secure and Practical Offloading of Machine Learning Inferences across IoT Devicescited by 1
  38. 2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1

50 most cited of 67 All 67 (JSON)