privacy-preserving
This term denotes techniques designed to protect individual privacy when collecting or analyzing data in AI applications. Methods like differential privacy aim to provide assurances that outputs do not compromise the privacy of individuals in the dataset.
- A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
- Don’t call it privacy-preserving or human-centric pose estimation if you don’t measure privacy
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
- FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models
- FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition
- Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
- Nearly-Linear Time and Massively Parallel Algorithms for $k$-anonymity
- Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
- Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation