TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Protect your art against AI/machine learning theft with customizable watermarks

13 点作者 jbothma大约 2 年前

2 条评论

yarg大约 2 年前
People have already succeeded in generating adversarial images that confuse neural networks.<p>Until networks reach the point where those techniques don&#x27;t work any more, it&#x27;s probably a better option - it allows you to automatically perturb the image for a targeted deception, as opposed to specifically defining a large number of parameters without understanding what the impact will be.
antiterra大约 2 年前
But does it work?
评论 #35809623 未加载