On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach | Journal of Artificial Intelligence Research#Privacy#Utility#Tradeoff#Machine Learning#Federated Learning#Paper#PDF·jair.org·Feb 12, 2024On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach | Journal of Artificial Intelligence Research
Scalable Extraction of Training Data from (Production) Language Models#Privacy#Security#ChatGPT#Paper#PDF·arxiv.org·Nov 30, 2023Scalable Extraction of Training Data from (Production) Language Models
Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data#Metaverse#VR#Privacy#Paper#PDF·arxiv.org·Feb 21, 2023Unique Identification of 50,000+ Virtual Reality Users from Head & Hand Motion Data