Data to 7 Oct 2026

CrypTFlow2: Practical 2-Party Secure Inference

arXiv 2010.06457 ↗First posted 13 Oct 2020cs.CR cs.LGcited by 82

Not on the map. Why?

Abstract (arXiv)

We present CrypTFlow2, a cryptographic framework for secure inference over realistic Deep Neural Networks (DNNs) using secure 2-party computation. CrypTFlow2 protocols are both correct -- i.e., their outputs are bitwise equivalent to the cleartext execution -- and efficient -- they outperform the state-of-the-art protocols in both latency and scale. At the core of CrypTFlow2, we have new 2PC protocols for secure comparison and division, designed carefully to balance round and communication complexity for secure inference tasks. Using CrypTFlow2, we present the first secure inference over ImageNet-scale DNNs like ResNet50 and DenseNet121. These DNNs are at least an order of magnitude larger than those considered in the prior work of 2-party DNN inference. Even on the benchmarks considered by prior work, CrypTFlow2 requires an order of magnitude less communication and 20x-30x less time than the state-of-the-art.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 15; 2023: 16; 2024: 18; 2025: 10; 2026: 14.

82 papers.

Sort:

By area:

2021Trustworthy AI: From Principles to Practicescited by 206
2022Selective Network Linearization for Efficient Private Inferencecited by 31
2021SIRNN: A Math Library for Secure RNN Inferencecited by 28
2023A Survey of Trustworthy Federated Learning with Perspectives on Security, Robustness, and Privacycited by 24
2024TRUCE: Private Benchmarking to Prevent Contamination and Improve Comparative Evaluation of LLMscited by 24
2023LLMs Can Understand Encrypted Prompt: Towards Privacy-Computing Friendly Transformerscited by 20
2022MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attentioncited by 19
2023Bytes Are All You Need: Transformers Operating Directly On File Bytescited by 16
2021Secure Quantized Training for Deep Learningcited by 15
2024Nimbus: Secure and Efficient Two-Party Inference for Transformerscited by 15
2021Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learningcited by 14
2024SLIP: Securing LLMs IP Using Weights Decompositioncited by 13

38 more

2022SecGNN: Privacy-Preserving Graph Neural Network Training and Inference as a Cloud Servicecited by 10
2022Split HE: Fast Secure Inference Combining Split Learning and Homomorphic Encryptioncited by 9
2023HyPHEN: A Hybrid Packing Method and Optimizations for Homomorphic Encryption-Based Neural Networkscited by 9
2023East: Efficient and Accurate Secure Transformer Framework for Inferencecited by 9
2024EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMscited by 9
2025CipherPrune: Efficient and Scalable Private Transformer Inferencecited by 9
2022A Practical Cross-Device Federated Learning Framework over 5G Networkscited by 7
2024Comet: A Communication-efficient and Performant Approximation for Private Transformer Inferencecited by 7
2023Lumos: Heterogeneity-aware Federated Graph Learning over Decentralized Devicescited by 6
2023NeuJeans: Private Neural Network Inference with Joint Optimization of Convolution and FHE Bootstrappingcited by 6
2021Unsupervised Information Obfuscation for Split Inference of Neural Networkscited by 5
2022SafeNet: The Unreasonable Effectiveness of Ensembles in Private Collaborative Learningcited by 5
2023Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryptioncited by 5
2023Falcon: Accelerating Homomorphically Encrypted Convolutions for Efficient Private Mobile Network Inferencecited by 5
2024MPC-Minimized Secure LLM Inferencecited by 5
2022GAN-based Domain Inference Attackcited by 4
2022Protecting Split Learning by Potential Energy Losscited by 3
2024CipherDM: Secure Three-Party Inference for Diffusion Model Samplingcited by 3
2024UTrace: Poisoning Forensics for Private Collaborative Learningcited by 3
2024CryptoTrain: Fast Secure Training on Encrypted Datasetcited by 3
2021Fast Privacy-Preserving Text Classification based on Secure Multiparty Computationcited by 2
2021Masked LARk: Masked Learning, Aggregation and Reporting worKflowcited by 2
2022Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inferencecited by 2
2022Efficient ML Models for Practical Secure Inferencecited by 2
2022PolyMPCNet: Towards ReLU-free Neural Architecture Search in Two-party Computation Based Private Inferencecited by 2
2023WW-FL: Secure and Private Large-Scale Federated Learningcited by 2
2023Defending Label Inference Attacks in Split Learning under Regression Settingcited by 2
2023Approximating ReLU on a Reduced Ring for Efficient MPC-based Private Inferencecited by 2
2024HEQuant: Marrying Homomorphic Encryption and Quantization for Communication-Efficient Private Inferencecited by 2
2026Minim: Privacy-Aware Minimal View for Agents via Trusted Local Sanitizationcited by 2
2022CECILIA: Comprehensive Secure Machine Learning Frameworkcited by 1
2023HE-MAN -- Homomorphically Encrypted MAchine learning with oNnx modelscited by 1
2023Compact: Approximating Complex Activation Functions for Secure Computationcited by 1
2024Ensembler: Protect Collaborative Inference Privacy from Model Inversion Attack via Selective Ensemblecited by 1
2024Pencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumptioncited by 1
2024Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defensecited by 1
2024Privacy-Preserving Hierarchical Model-Distributed Inferencecited by 1
2024PrivQuant: Communication-Efficient Private Inference with Quantized Network/Protocol Co-Optimizationcited by 1

50 most cited of 82 All 82 (JSON)