data privacy
Data privacy in AI relates to the protection of personal and sensitive information used in training datasets. Maintaining data privacy is essential to comply with regulations and to ensure ethical data use in AI applications.
- Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
- Efficient Verified Unlearning For Distillation
- Enhancing Privacy in Multimodal Federated Learning with Information Theory
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts
- FedEL: Federated Elastic Learning for Heterogeneous Devices
- FedIGL: Federated Invariant Graph Learning for Non-IID Graphs
- How Well Can Differential Privacy Be Audited in One Run?
- MARS: A Malignity-Aware Backdoor Defense in Federated Learning
- Memorization in Graph Neural Networks
- NoBOOM: Chemical Process Datasets for Industrial Anomaly Detection
- On the Edge of Memorization in Diffusion Models
- OpenUnlearning: Accelerating LLM Unlearning via Unified Benchmarking of Methods and Metrics
- Optimal Regret of Bandits under Differential Privacy
- Towards Robust Parameter-Efficient Fine-Tuning for Federated Learning