privacy concerns
Privacy concerns in AI encompass the ethical and legal challenges associated with data collection, usage, and sharing, particularly regarding the handling of personal data and ensuring user confidentiality in compliance with regulations such as GDPR.
- Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
- An Investigation of Memorization Risk in Healthcare Foundation Models
- Environment Inference for Learning Generalizable Dynamical System
- Generating Multi-Table Time Series EHR from Latent Space with Minimal Preprocessing
- Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities
- LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models
- Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
- PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture
- Stop the Nonconsensual Use of Nude Images in Research
- UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation