Privacy-Preserving ML Comparison Hub
4 papers - avg viability 5.5
Top Papers
- Almost-Free Queue Jumping for Prior Inputs in Private Neural Inference(7.0)
PrivQJ enhances privacy-preserving neural network inference by enabling efficient priority handling for urgent requests.
- Tiny, Hardware-Independent, Compression-based Classification(7.0)
Enable client-side machine learning with a hardware-independent, compression-based classification model that protects user privacy and minimizes computational costs.
- SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy(5.0)
A unified cryptographic and differential privacy framework for collaborative machine learning.
- Informationally Compressive Anonymization: Non-Degrading Sensitive Input Protection for Privacy-Preserving Supervised Machine Learning(3.0)
A novel privacy-preserving ML framework that ensures strong privacy guarantees without degrading performance.