Privacy-Preserving AI Comparison Hub
4 papers - avg viability 5.8
Top Papers
- Nonparametric Variational Differential Privacy via Embedding Parameter Clipping(7.0)
A novel approach to enhance privacy in language models through parameter clipping, improving the privacy-utility trade-off.
- MPU: Towards Secure and Privacy-Preserving Knowledge Unlearning for Large Language Models(5.0)
A privacy-preserving framework enabling localized knowledge unlearning for language models without server-client parameter exchange.
- StegaFFD: Privacy-Preserving Face Forgery Detection via Fine-Grained Steganographic Domain Lifting(5.0)
A novel framework for privacy-preserving face forgery detection using steganography to mask sensitive data without alerting attackers.