Keep Moving Forward
Denoising Diffusion Probabilistic Models 阅读笔记 Denoising Diffusion Probabilistic Models 阅读笔记
Denoising Diffusion Probabilistic Models 阅读笔记论文题目：Denoising Diffusion Probabilistic Models 发表时间：2020 发表期刊/会议：NIPS 期刊
2025-02-17 wangxh
论文笔记 成员推理 扩散模型
Are Diffusion Models Vulnerable to Membership Inference Attacks 阅读笔记 Are Diffusion Models Vulnerable to Membership Inference Attacks 阅读笔记
Are Diffusion Models Vulnerable to Membership Inference Attacks 阅读笔记论文题目：Are Diffusion Models Vulnerable to Membership I
2024-12-29 wangxh
论文笔记 成员推理 扩散模型
Do Membership Inference Attacks Work on Large Language Models 阅读笔记 Do Membership Inference Attacks Work on Large Language Models 阅读笔记
论文研读笔记论文题目：Do Membership Inference Attacks Work on Large Language Models?发表时间：2024发表期刊/会议：COLM论文作者：Duan et al. 1. 内容简介论文
2024-11-30 wangxh
Low-Cost High-Power Membership Inference Attacks 阅读笔记 Low-Cost High-Power Membership Inference Attacks 阅读笔记
论文研读笔记论文题目：Low-Cost High-Power Membership Inference Attacks发表时间：2024发表期刊/会议：ICML 1. 内容简介这篇文章通过重新设计评分函数，成功实现了一种资源消耗更低、TPR
2024-11-29 wangxh
论文笔记 成员推理
OSLO: One-Shot Label-Only Membership Inference Attacks 阅读笔记 OSLO: One-Shot Label-Only Membership Inference Attacks 阅读笔记
论文研读笔记论文题目：OSLO: One-Shot Label-Only Membership Inference Attacks发表时间：2024发表期刊/会议：To appear at NeurIPS 2024 1. 内容简介在只能访问
2024-11-23 wangxh
论文笔记 成员推理
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly 阅读笔记 A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly 阅读笔记
论文研读笔记（2-3页）论文题目：A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly 发表时间：2024
2024-09-22 wangxh
机器学习 综述 大语言模型
2 / 4