mlsanityData to 7 Oct 2026

FALCON: Honest-Majority Maliciously Secure Framework for Private Deep Learning

arXiv 2004.02229 ↗First posted 5 Apr 2020cs.CR cs.LGcited by 74

Not on the map. Why?

Abstract (arXiv)

We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such as VGG16 (ii) it supports batch normalization which is important for training complex networks such as AlexNet (iii) Falcon guarantees security with abort against malicious adversaries, assuming an honest majority (iv) Lastly, Falcon presents new theoretical insights for protocol design that make it highly efficient and allow it to outperform existing secure deep learning solutions. Compared to prior art for private inference, we are about 8x faster than SecureNN (PETS'19) on average and comparable to ABY3 (CCS'18). We are about 16-200x more communication efficient than either of these. For private training, we are about 6x faster than SecureNN, 4.4x faster than ABY3 and about 2-60x more communication efficient. Our experiments in the WAN setting show that over large networks and datasets, compute operations dominate the overall latency of MPC, as opposed to the communication.

Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 12; 2023: 14; 2024: 18; 2025: 16; 2026: 2.

74 papers.

Sort:

By area:

  1. 2021CrypTen: Secure Multi-Party Computation Meets Machine Learningcited by 131
  2. 2021Differential Privacy for Text Analytics via Natural Text Sanitizationcited by 74
  3. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  4. 2021CryptGPU: Fast Privacy-Preserving Machine Learning on the GPUcited by 46
  5. 2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
  6. 2022Differential Privacy Guarantees for Stochastic Gradient Langevin Dynamicscited by 18
  7. 2021Circa: Stochastic ReLUs for Private Deep Learningcited by 16
  8. 2021Secure Quantized Training for Deep Learningcited by 15
  9. 2023On the Trustworthiness Landscape of State-of-the-art Generative Models: A Survey and Outlookcited by 15
  10. 2021Privacy-Preserving Video Classification with Convolutional Neural Networkscited by 10
  11. 2022SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Servicecited by 10
  12. 2021SoK: Machine Learning Governancecited by 9
38 more
  1. 2022SecureFedYJ: a safe feature Gaussianization protocol for Federated Learningcited by 9
  2. 2023PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attackscited by 9
  3. 2021Tetrad: Actively Secure 4PC for Secure Training and Inferencecited by 8
  4. 2023A Survey of Secure Computation Using Trusted Execution Environmentscited by 8
  5. 2022Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacycited by 7
  6. 2023Label Inference Attack against Split Learning under Regression Settingcited by 7
  7. 2024Ditto: Quantization-aware Secure Inference of Transformers upon MPCcited by 7
  8. 2025Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systemscited by 6
  9. 2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
  10. 2023GPU-based Private Information Retrieval for On-Device Machine Learning Inferencecited by 5
  11. 2023Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryptioncited by 5
  12. 2024MPC-Minimized Secure LLM Inferencecited by 5
  13. 2024Unlocking Visual Secrets: Inverting Features with Diffusion Priors for Image Reconstructioncited by 5
  14. 2021Adam in Private: Secure and Fast Training of Deep Neural Networks with Adaptive Moment Estimationcited by 4
  15. 2022SCOTCH: An Efficient Secure Computation Framework for Secure Aggregationcited by 4
  16. 2022MPC-Pipe: an Efficient Pipeline Scheme for Secure Multi-party Machine Learning Inferencecited by 4
  17. 2025SpecPipe: Accelerating Pipeline Parallelism-based LLM Inference with Speculative Decodingcited by 4
  18. 2021MPCLeague: Robust MPC Platform for Privacy-Preserving Machine Learningcited by 3
  19. 2024SSNet: A Lightweight Multi-Party Computation Scheme for Practical Privacy-Preserving Machine Learning Service in the Cloudcited by 3
  20. 2024UTrace: Poisoning Forensics for Private Collaborative Learningcited by 3
  21. 2024CryptoTrain: Fast Secure Training on Encrypted Datasetcited by 3
  22. 2025Comet: Accelerating Private Inference for Large Language Model by Predicting Activation Sparsitycited by 3
  23. 2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
  24. 2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
  25. 2024Wildest Dreams: Reproducible Research in Privacy-preserving Neural Network Trainingcited by 2
  26. 2022CECILIA: Comprehensive Secure Machine Learning Frameworkcited by 1
  27. 2022MPClan: Protocol Suite for Privacy-Conscious Computationscited by 1
  28. 2022Private Multiparty Perception for Navigationcited by 1
  29. 2022A Survey of Face Recognitioncited by 1
  30. 2023On Achieving Privacy-Preserving State-of-the-Art Edge Intelligencecited by 1
  31. 2023Securing Neural Networks with Knapsack Optimizationcited by 1
  32. 2023Towards Fast and Scalable Private Inferencecited by 1
  33. 2023Compact: Approximating Complex Activation Functions for Secure Computationcited by 1
  34. 2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1
  35. 2024S2NeRF: Privacy-preserving Training Framework for NeRFcited by 1
  36. 2025Covert Attacks on Machine Learning Training in Passively Secure MPCcited by 1
  37. 2025SecP-Tuning: Efficient Privacy-Preserving Prompt Tuning for Large Language Models via MPCcited by 1
  38. 2025Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharingcited by 1

50 most cited of 74 All 74 (JSON)