论文笔记

大模型笔记

大模型笔记

【论文笔记】Backdooring Multimodal Learning

【论文笔记】Backdooring Multimodal Learning

【论文笔记】Chaotic Weights： A Novel Approach to Protect Intellectual Property of Deep Neural Networks

【论文笔记】Chaotic Weights： A Novel Approach to Protect Intellectual Property of Deep Neural Networks

【论文笔记】DeepACO Neural-enhanced Ant Systems for Combinatorial Optimization

【论文笔记】DeepACO Neural-enhanced Ant Systems for Combinatorial Optimization

【论文笔记】FEDML-HE_AN EFFICIENT HOMOMORPHIC-ENCRYPTION-BASED PRIVACY-PRESERVING FEDERATED LEARNING SYSTEM

【论文笔记】FEDML-HE_AN EFFICIENT HOMOMORPHIC-ENCRYPTION-BASED PRIVACY-PRESERVING FEDERATED LEARNING SYSTEM

【论文笔记】Data-free Backdoor Removal based on Channel Lipschitzness

【论文笔记】Data-free Backdoor Removal based on Channel Lipschitzness

【论文笔记】Deep Learning with Differential Privacy

简介 开创了通过向深度学习模型的梯度进行加噪从而实现差分隐私的方法 什么是差分隐私 差分隐私就是对两个相邻数据库有如下定义： 简单来说，假设有两个数据库，两个