publications

2024

1. Memory Efficient Privacy-Preserving Machine Learning Based on Homomorphic Encryption

   Robert Podschwadt, Parsa Ghazvinian, Mohammad GhasemiGol, and 1 more author

   In International Conference on Applied Cryptography and Network Security, 2024

2023

1. Privacy-Preserving Deep Learning with Homomorphic Encryption: Addressing Challenges Related to Usability, Memory, and Recurrent Neural Networks

   Robert Podschwadt

   2023

2022

1. A Survey of Deep Learning Architectures for Privacy-Preserving Machine Learning With Fully Homomorphic Encryption

   Robert Podschwadt, Daniel Takabi, Peizhao Hu, and 2 more authors

   IEEE Access, 2022

   Conference Name: IEEE Access

   Abs

   Outsourced computation for neural networks allows users access to state-of-the-art models without investing in specialized hardware and know-how. The problem is that the users lose control over potentially privacy-sensitive data. With homomorphic encryption (HE), a third party can perform computation on encrypted data without revealing its content. In this paper, we reviewed scientific articles and publications in the particular area of Deep Learning Architectures for Privacy-Preserving Machine Learning (PPML) with Fully HE. We analyzed the changes to neural network models and architectures to make them compatible with HE and how these changes impact performance. Next, we find numerous challenges to HE-based privacy-preserving deep learning, such as computational overhead, usability, and limitations posed by the encryption schemes. Furthermore, we discuss potential solutions to the HE PPML challenges. Finally, we propose evaluation metrics that allow for a better and more meaningful comparison of PPML solutions.

2021

1. Non-interactive Privacy Preserving Recurrent Neural Network Prediction with Homomorphic Encryption

   Robert Podschwadt, and Daniel Takabi

   In 2021 IEEE 14th International Conference on Cloud Computing (CLOUD), 2021
2. Neurocrypt: Machine learning over encrypted distributed neuroimaging data

   Nipuna Senanayake, Robert Podschwadt, Daniel Takabi, and 2 more authors

   Neuroinformatics, 2021

   Publisher: Springer

2020

1. Classification of Encrypted Word Embeddings using Recurrent Neural Networks.

   Robert Podschwadt, and Daniel Takabi

   In PrivateNLP@ WSDM, 2020

2019

1. Privacy preserving neural network inference on encrypted data with GPUs

   Daniel Takabi, Robert Podschwadt, Jeff Druce, and 2 more authors

   arXiv preprint arXiv:1911.11377, 2019
2. On Effectiveness of Adversarial Examples and Defenses for Malware Classification

   Robert Podschwadt, and Hassan Takabi

   In International Conference on Security and Privacy in Communication Systems, 2019