Open Source Software
OpenFL is a Python 3 framework for Federated Learning. OpenFL is designed to be a flexible, extensible and easily learnable tool for data scientists. OpenFL is developed by Intel Internet of Things Group (IOTG) and Intel Labs. Please find it here.
FedML open source library has been used widely in the world, including researchers and engineers from the United States, Canada, China, Germany, Denmark, Korea, and Singapore. Some of them are from big companies Google, Amazon, Adobe, Cisco, and Huawei, as well as well-known research-oriented universities such as Stanford, Princeton, USC, HKUST, Tsinghua, etc. They published in top-tier AI conferences including ICML, NeurIPS, ICLR, and AAAI. Please find it here.
- ABY2.0: Improved mixed-protocol secure two-party computation, Arpita Patra, Thomas Schneider, Ajith Suresh, Hossein Yalame
- A generic hybrid 2PC framework with application to private inference of unmodified neural networks, Lennart Braun, Rosario Cammarota, and Thomas Schneider
- Analysis of Machine Learning Approaches to Packing Detection, Bertrand Van Ouytsel, Charles-Henry; Given-Wilson, Thomas; Minet, Jeremy; Roussieau, Julian; Legay, Axel
- An efficient and practical privacy-preserving kidney exchange problem protocol, Timm Birka, Tobias Kussel, Helen Möllering, and Thomas Schneider
- BaFFLe: Backdoor detection via feedback-based federated learning, Sébastien Andreina, Giorgia Azzurra Marson, Helen Möllering, Ghassan Karame
- AutoRank: Automated Rank Selection for Effective Neural Network Customization, Javaheripi, Mojan, Mohammad Samragh, and Farinaz Koushanfar
- Balancing quality and efficiency in private clustering with affinity propagation, Hannah Keller, Helen Möllering, Thomas Schneider, Hossein Yalame
- Basil: A Fast and Byzantine-Resilient Approach for Decentralized Training, R. El Kordy, S. Prakash, and A.S. Avestimehr
- Byzantine-Resilient Secure Federated Learning, Jinhyun So, Basak Guler, Salman Avestimehr
- CaPC Learning: Confidential and Private Collaborative Learning, Christopher A. Choquette-Choo, Natalie Dullerud, Adam Dziedzic, Yunxiang Zhang, Somesh Jha, Nicolas Papernot, Xiao Wang
- CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning, Jinhyun So, Basak Guler, Salman Avestimehr
- CodedReduce: A Fast and Robust Framework for Gradient Aggregation in Distributed Learning, A. Reisizadeh, S. Prakash, R. Pedarsani, and A.S. Avestimehr
- CURE: A Security Architecture with CUstomizable and Resilient Enclaves, R. Bahmani, F. Brasser, G. Dessouky, P. Jauernig, M. Klimmek, A.-R. Sadeghi, E. Stapf
- DAWN: Dynamic Adversarial Watermarking of Neural Networks, S. Szyller et al.
- Deep Neural Network Fingerprinting by Conferrable Adversarial Examples, N. Lukas, Y. Zhang, F. Kerschbaum
- DEMO: AirCollect: Efficiently recovering hashed phone numbers leaked via Apple AirDrop, Alexander Heinrich, Matthias Hollick, Thomas Schneider, Milan Stute, and Christian Weinert
- Detection and classification of malware based on symbolic execution and machine learning methods, Bertrand Van Ouytsel, Charles-Henry ; Legay, Axel
- Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent, Rishav Chourasia*, Jiayuan Ye*, and Reza Shokri
- Ditto: Fair and Robust Federated Learning Through Personalization, T. Li, S. Hu, A. Beirami, V. Smith
- ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning, Lutz, Oliver; Chen, Huili; Fereidooni, Hossein; Sendner, Christoph; Dmitrienko, Alexandra; Sadeghi, Ahmad Reza;
- Exploitation Techniques for Data-Oriented Attacks with Existing and Potential Defense Approaches, Salman Ahmed et al.
- FairFed: Enabling Group Fairness in Federated Learning, Y. Ezzeldin, S. Yan, C. He, E. Ferrara, and A.S. Avestimehr
- Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharing, M. Khodak, R. Tu, T. Li, L. Li, M.-F. Balcan, V. Smith, A. Talwalkar
- Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection, T. Zhang, C. He, T. Ma, L. Gao, M. Ma, and A.S. Avestimehr
- FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks, C. He, et al, M. Annavaram, S. Avestimehr
- Fundamental resource trade-offs for encoded distributed optimization, A S. Avestimehr, S.M. Kalan, and M. Soltanolkotabi
- GrandDetAuto: Detecting Malicious Nodes in Large-Scale Autonomous Network, Abera et al.
- Heterogeneity for the Win: One-Shot Federated Clustering, D. Dennis, T. Li, V. Smith
- Improved circuit compilation for hybrid MPC via compiler intermediate representation, Daniel Demmler, Stefan Katzenbeisser, Thomas Schneider, Tom Schuster, Christian Weinert
- Label-Only Membership Inference Attacks, Christopher A. Choquette Choo, Florian Tramer, Nicholas Carlini, Nicolas Papernot
- LLVM-based circuit compilation for practical secure computation, Tim Heldmann, Thomas Schneider, Oleksandr Tkachenko, Christian Weinert, Hossein Yalame
- Low-Cost Hiding of the Query Pattern, Maryam Sepehri, Florian Kerschbaum
- Manipulating SGD with Data Ordering Attacks, Ilia Shumailov, Zakhar Shumaylov, Dmitry Kazhdan, Yiren Zhao, Nicolas Papernot, Murat A. Erdogdu, Ross Anderson
- On Large-Cohort Training for Federated Learning, Z. Charles, Z. Garrett, Z. Huo, S. Shmulyian, V. Smith
- On the Privacy Risks of Algorithmic Fairness, Hongyan Chang, Reza Shokri
- On the Privacy Risks of Model Explanations, Reza Shokri, Martin Strobel, Yair Zick
- On the Robustness of Backdoor-based Watermarking in Deep Neural Networks, M. Shafieinejad et al.
- PACStack: an Authenticated Call Stack, Hans Liljestrand, Thomas Nyman, Lachlan J. Gunn, Jan-Erik Ekberg, N. Asokan
- PCOR: Private Contextual Outlier Release via Differentially Private Search, M. Shafieinejad, F. Kerschbaum, I. Ilyas
- PrivateDrop: Practical privacy-preserving authentication for Apple AirDrop, Alexander Heinrich, Matthias Hollick, Thomas Schneider, Milan Stute, Christian Weinert
- Privacy-preserving density-based clustering, Beyza Bozdemir, Sébastien Canard, Orhan Ermis, Helen Möllering, Melek Önen, and Thomas Schneider
- Private training with trusted hardware, H. Hashemi, Y. Wang, M. Annavaram
- ProFlip: Targeted Trojan Attack with Progressive Bit Flips, Huili Chen, Cheng Fu, Jishen Zhao, Farinaz Koushanfar
- Proof-of-Learning: Definitions and Practice, Hengrui Jia, Mohammad Yaghini, Christopher A. Choquette-Choo, Natalie Dullerud, Anvith Thudi, Varun Chandrasekaran, Nicolas Papernot
- Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models, Sasi Kumar Murakonda, Reza Shokri, and George Theodorakopoulos
- Revisiting hybrid private information retrieval, Daniel Günther, Thomas Schneider, and Felix Wiegand
- RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks, T. Wang, F. Kerschbaum
- SAFELearn: Secure aggregation for private federated learning, Hossein Fereidooni, Samuel Marchal, Markus Miettinen, Azalia Mirhoseini, Helen Möllering, Thien Duc Nguyen, Phillip Rieger, Ahmad-Reza Sadeghi, Thomas Schneider, Hossein Yalame, and Shaza Zeitouni
- Secure Aggregation for Buffered Asynchronous Federated Learning, J. So, R. Ali, B. Guker, and A.S. Avestimehr
- SoK: Efficient privacy-preserving clustering, Aditya Hegde, Helen Möllering, Thomas Schneider, and Hossein Yalame
- SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks, C. He, E. Ceyani, K. Balasubramanian, M. Annavaram, and A. S. Avestimehr
- SynCirc: Efficient synthesis of depth-optimized circuits for secure computation, Arpita Patra, Thomas Schneider, Ajith Suresh, and Hossein Yalame
- Tilted Empirical Risk Minimization, Li, T. Beirami, A., Sanjabi, M. Smith, V.
- Turbo-Aggregate: Breaking the Quadratic Aggregation Barrier in Secure Federated Learning, Jinhyun So, Basak Guler, Salman Avestimehr
- Two Sides of Meta-Learning Evaluation: In vs. Out of Distribution, A. Setlur*, O. Li*, V. Smith
- VASA: Vector AES instructions for Security Applications, Jean-Pierre Münch, Thomas Schneider, and Hossein Yalame
- WAFFLE: Watermarking in Federated Learning, Buse Atli et al.