copy and paste this google map to your website or blog!
Press copy button and paste into your blog or website.
(Please switch to 'HTML' mode when posting into your blog. Examples: WordPress Example, Blogger Example)
Ruoxin Chen | IEEE Xplore Author Details Ruoxin Chen received the BS degree in mathematics and statistics from Wuhan University, Wuhan, China, in 2014, and the PhD degree from the School of Computer Science, Shanghai Jiaotong University, in 2023 He is currently a senior researcher with the Youtu Laboratory, Tencent, China
GitHub - roy-ch Dual-Data-Alignment: This repository is the official . . . Winning model trained exclusively on DDA-aligned COCO (no face data) A model with zero face data won a face anti-spoofing competition The rapid increase in AI-generated images (AIGIs) underscores the need for detection methods
【AAAI2022】自适应的随机平滑防御的鲁棒性认证方法 - 知乎 本文介绍被AAAI22接收的新工作。 我们是第一个探索了 针对随机平滑 (Randomized Smoothing)的高效的针对随机平滑的鲁棒性认证方法。 随机平滑是一种常见且 SOTA 的认证防御 (certified defense),但其一个主要缺点在于 鲁棒认证的时候计算开销过大。 论文题目:Input-Specific Robustness Certification for Randomized Smoothing 作者信息:Ruoxin Chen, Jie Li*, Junchi Yan, Ping Li, Bin Sheng 关键词:对抗攻击、可认证鲁棒、鲁棒性认证 那么现在问题在于,对于每个输入我如何确定该选用多大的采样数。
roy-ch (Ruoxin Chen) · GitHub This repository is the official implementation of NeurIPS 2025 Paper "Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable"