Comparison of Fully Homomorphic Encryption and Garbled Circuits approaches in Privacy-Preserving Machine Learning

Machine Learning (ML) is making its way into fields such as healthcare, finance, and natural language processing (NLP), and concerns over data privacy and model confidentiality continue to grow. Privacy-Preserving Machine Learning (PPML) addresses this challenge by enabling inference on private data without revealing sensitive inputs or proprietary models. Leveraging Secure Computation techniques from Cryptography, two widely studied approaches in this domain are Fully Homomorphic Encryption (FHE) and Garbled Circuits (GC). This thesis presents a comparative evaluation of FHE and GC for secure neural network inference (SNNI). A two-layer neural network (NN) was implemented using the CKKS scheme from the Microsoft SEAL library (FHE) and the TinyGarble2.0 framework (GC) by IntelLabs. Both implementations are evaluated under a semi-honest threat model, measuring inference output error, round-trip time, peak memory usage, communication overhead, and communication rounds. Results reveal a trade-off: modular GC offers faster execution and lower memory consumption, while FHE supports non-interactive inference. The reproducible implementations aid secure model deployments in real-world ML-as-a-Service (MLaaS) settings.