Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training

13 June 2023

Papers citing "Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP Training"

5 / 5 papers shown

Title
BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation Junnan Li Dongxu Li Caiming Xiong Guosheng Lin MLLM BDL VLM CLIP 392 4,154 0 28 Jan 2022
Differentially Private Fine-tuning of Language Models Da Yu Saurabh Naik A. Backurs Sivakanth Gopi Huseyin A. Inan ... Y. Lee Andre Manoel Lukas Wutschitz Sergey Yekhanin Huishuai Zhang 134 347 0 13 Oct 2021
Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts Soravit Changpinyo P. Sharma Nan Ding Radu Soricut VLM 299 1,084 0 17 Feb 2021
Understanding self-supervised Learning Dynamics without Contrastive Pairs Yuandong Tian Xinlei Chen Surya Ganguli SSL 138 281 0 12 Feb 2021
Tempered Sigmoid Activations for Deep Learning with Differential Privacy Nicolas Papernot Abhradeep Thakurta Shuang Song Steve Chien Ulfar Erlingsson AAML 147 178 0 28 Jul 2020