Multi-Party-Learning-Related-Papers

This is a repository for resources on all kinds of things of Multi-Party Learning frameworks. Currently it's maintained by Daslab of Fudan University. All these papers are sorted by time and seperated by category. Any suggestions and pull requests are welcome. This repository is only for research purpose. If any authors don't want their paper to be listed here, please feel free to contact us.

This repository will focus on:

• 1. Frameworks of Multi-Party Learning.
• 2. Theories of Multi-Party Learning.

Table of Contents

• Crypto
• ACM CCS
• ACM SIGMOD
• IEEE S&P
• Usenix-Security
• NDSS
• SIGKDD
• ACM TOPS
• PETS
• ArXiv

Crypto

• Multiparty computation from somewhat homomorphic encryption Damgård, Ivan, et al. "Multiparty computation from somewhat homomorphic encryption." Annual Cryptology Conference. Springer, Berlin, Heidelberg, 2012.

• Traceable Secret Sharing and Applications Goyal, Vipul, Yifan Song, and Akshayaram Srinivasan. "Traceable secret sharing and applications." Annual International Cryptology Conference. Springer, Cham, 2021.

ACM-SIGMOD

• IncShrink: Architecting Efficient Outsourced Databases using Incremental MPC and Differential PrivacyWang C, Bater J, Chenghong Wang, Johes Bater, Kartik Nayak, and Ashwin Machanavajjhala. 2022. IncShrink: Architecting Efficient Outsourced Databases using Incremental MPC and Differential Privacy. In Proceedings of the 2022 International Conference on Management of Data (SIGMOD '22). Association for Computing Machinery, New York, NY, USA, 818–832.

• Prism: Private Verifiable Set Computation over Multi-Owner Outsourced Databases Li, Yin, et al. "Prism: private verifiable set computation over multi-owner outsourced databases." Proceedings of the 2021 International Conference on Management of Data. 2021.

ACM-CCS

• ASTRA: high throughput 3pc over rings with application to secure prediction Chaudhari, Harsh, et al. "ASTRA: high throughput 3pc over rings with application to secure prediction." Proceedings of the 2019 ACM SIGSAC Conference on Cloud Computing Security Workshop. 2019.

• QUOTIENT: two-party secure neural network training and prediction Agrawal, Nitin, et al. "QUOTIENT: two-party secure neural network training and prediction." Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security. 2019.

• MP-SPDZ: A versatile framework for multi-party computation Keller, Marcel. "MP-SPDZ: A versatile framework for multi-party computation." Proceedings of the 2020 ACM SIGSAC conference on computer and communications security. 2020.

• Cryptflow2: Practical 2-party secure inference Rathee, Deevashwer, et al. "CrypTFlow2: Practical 2-party secure inference." Proceedings of the 2020 ACM SIGSAC Conference on Computer and Communications Security. 2020.

• COINN: Crypto/ML Codesign for Oblivious Inference via Neural Networks Hussain, Siam Umar, et al. "COINN: Crypto/ML Codesign for Oblivious Inference via Neural Networks." Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security. 2021.

• Fast Fully Secure Multi-Party Computation over Any Ring with Two-Thirds Honest Majority Dalskov, Anders, Daniel Escudero, and Ariel Nof. "Fast Fully Secure Multi-Party Computation over Any Ring with Two-Thirds Honest Majority." Cryptology ePrint Archive (2022).

• SECFLOAT: Accurate Floating-Point meets Secure 2-Party Computation Rathee, Deevashwer, et al. "SecFloat: Accurate Floating-Point meets Secure 2-Party Computation." Cryptology ePrint Archive (2022).

• NFGen: Automatic Non-linear Function Evaluation Code Generator for General-purpose MPC PlatformsFan, Xiaoyu, et al. "NFGen: Automatic Non-linear Function Evaluation Code Generator for General-purpose MPC Platforms." Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security (2022).

• pmpl: A robust multi-party learning framework with a privileged partySong, Lushan, et al. "pmpl: A robust multi-party learning framework with a privileged party." Proceedings of the 2022 ACM SIGSAC Conference on Computer and Communications Security. (2022)

IEEE-S&P

• Helen: Maliciously Secure Coopetitive Learning for Linear Models Zheng, Wenting, et al. "Helen: Maliciously secure coopetitive learning for linear models." 2019 IEEE Symposium on Security and Privacy (SP). IEEE, 2019.

• CRYPTFLOW: Secure TensorFlow Inference Kumar, Nishant, et al. "Cryptflow: Secure tensorflow inference." 2020 IEEE Symposium on Security and Privacy (SP). IEEE, 2020.

• Cryptgpu: Fast privacy-preserving machine learning on the gpu Tan, Sijun, et al. "CryptGPU: Fast privacy-preserving machine learning on the GPU." 2021 IEEE Symposium on Security and Privacy (SP). IEEE, 2021.

• SiRnn: A math library for secure RNN inference Rathee, Deevashwer, et al. "SiRnn: A math library for secure RNN inference." 2021 IEEE Symposium on Security and Privacy (SP). IEEE, 2021.

• Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy Ruan, Wenqiang, et al. "Private, Efficient, and Accurate: Protecting Models Trained by Multi-party Learning with Differential Privacy." arXiv preprint arXiv:2208.08662 (2022).

Usenix-Security

• {XONN}:{XNOR-based} Oblivious Deep Neural Network Inference Riazi, M. Sadegh, et al. "{XONN}:{XNOR-based} Oblivious Deep Neural Network Inference." 28th USENIX Security Symposium (USENIX Security 19). 2019.

• Delphi: A cryptographic inference service for neural networks Mishra, Pratyush, et al. "Delphi: A cryptographic inference service for neural networks." 29th USENIX Security Symposium (USENIX Security 20). 2020.

• {SWIFT}: Super-fast and Robust {Privacy-Preserving} Machine Learning Koti, Nishat, et al. "{SWIFT}: Super-fast and Robust {Privacy-Preserving} Machine Learning." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Fantastic Four:{Honest-Majority}{Four-Party} Secure Computation With Malicious Security Dalskov, Anders, Daniel Escudero, and Marcel Keller. "Fantastic Four:{Honest-Majority}{Four-Party} Secure Computation With Malicious Security." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Aby2.0: Improved mixed-protocol secure two-party computation Patra, Arpita, et al. "{ABY2. 0}: Improved {Mixed-Protocol} Secure {Two-Party} Computation." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Muse: Secure inference resilient to malicious clients Lehmkuhl, Ryan, et al. "Muse: Secure inference resilient to malicious clients." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Cerebro: A Platform for Multi-Party Cryptographic Collaborative Learning Zheng, Wenting, et al. "Cerebro: A Platform for {Multi-Party} Cryptographic Collaborative Learning." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Senate: A Maliciously-Secure MPC Platform for Collaborative Analytics Poddar, Rishabh, et al. "Senate: A {Maliciously-Secure}{MPC} Platform for Collaborative Analytics." 30th USENIX Security Symposium (USENIX Security 21). 2021.

• Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference Secure Poisson Regression Huang, Zhicong, et al. "Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference." IACR Cryptol. ePrint Arch. 2022 (2022): 207.

• Secure Poisson Regression Kelkar, Mahimna, et al. "Secure poisson regression." 31st USENIX Security Symposium (USENIX Security 22). 2022.

• Piranha: A GPU Platform for Secure Computation Jean-Luc Watson, et al. "Piranha: A GPU Platform for Secure Computation." 31st USENIX Security Symposium(USENIX Security 22). 2022.

• {ppSAT}: Towards {Two-Party} Private {SAT} Solving Luo, Ning, et al. "{ppSAT}: Towards {Two-Party} Private {SAT} Solving." 31st USENIX Security Symposium (USENIX Security 22). 2022.

NDSS

• ABY-A framework for efficient mixed-protocol secure two-party computation Demmler, Daniel, Thomas Schneider, and Michael Zohner. "ABY-A framework for efficient mixed-protocol secure two-party computation." NDSS. 2015.

• BLAZE: blazing fast privacy-preserving machine learning Patra, Arpita, and Ajith Suresh. "BLAZE: blazing fast privacy-preserving machine learning." arXiv preprint arXiv:2005.09042 (2020).

• Trident: Efficient 4pc framework for privacy preserving machine learning Chaudhari, Harsh, Rahul Rachuri, and Ajith Suresh. "Trident: Efficient 4pc framework for privacy preserving machine learning." arXiv preprint arXiv:1912.02631 (2019).

• GALA: Greedy ComputAtion for linear algebra in privacy-preserved neural networks Zhang, Qiao, Chunsheng Xin, and Hongyi Wu. "GALA: Greedy ComputAtion for linear algebra in privacy-preserved neural networks." arXiv preprint arXiv:2105.01827 (2021).

• Tetrad: Actively Secure 4PC for Secure Training and Inference Koti, Nishat, et al. "Tetrad: actively secure 4pc for secure training and inference." arXiv preprint arXiv:2106.02850 (2021).

ACM-SIGKDD

• When homomorphic encryption marries secret sharing: Secure large-scale sparse logistic regression and applications in risk control Chen, Chaochao, et al. "When homomorphic encryption marries secret sharing: Secure large-scale sparse logistic regression and applications in risk control." Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021.

ACM-TOPS

• MOTION - A Framework for Mixed-Protocol Multi-Party Computation Braun, Lennart, et al. "MOTION–A Framework for Mixed-Protocol Multi-Party Computation." ACM Transactions on Privacy and Security 25.2 (2022): 1-35.

PETS

• SecureNN: 3-Party Secure Computation for Neural Network Training Wagh, Sameer, Divya Gupta, and Nishanth Chandran. "SecureNN: 3-Party Secure Computation for Neural Network Training." Proc. Priv. Enhancing Technol. 2019.3 (2019): 26-49.

• FLASH: fast and robust framework for privacy-preserving machine learning Byali, Megha, et al. "FLASH: fast and robust framework for privacy-preserving machine learning." Cryptology ePrint Archive (2019).

• Secure Evaluation of Quantized Neural Networks Dalskov, Anders, Daniel Escudero, and Marcel Keller. "Secure evaluation of quantized neural networks." Proceedings on Privacy Enhancing Technologies 2020.4 (2020): 355-375.

• Falcon: Honest-Majority Maliciously Secure Framework for Private Deep Learning Wagh, Sameer, et al. "Falcon: Honest-majority maliciously secure framework for private deep learning." arXiv preprint arXiv:2004.02229 (2020).

ArXiv

• Ariann: Low-interaction privacy-preserving deep learning via function secret sharing Ryffel, Théo, et al. "Ariann: Low-interaction privacy-preserving deep learning via function secret sharing." arXiv preprint arXiv:2006.04593 (2020).

• Efficient ML Models for Practical Secure Inference Ganesan, Vinod, et al. "Efficient ML Models for Practical Secure Inference." arXiv preprint arXiv:2209.00411 (2022).

• Multi-Party Computation in the GDPR Helminger, Lukas, and Christian Rechberger. "Multi-Party Computation in the GDPR." Cryptology ePrint Archive (2022).