思想与社会2014 · 分享于 Hacker News
Explaining and Harnessing Adversarial Examples
探索《Explaining and Harnessing Adversarial Examples》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
Yrexpository ·
Supabase MCP can leak your entire SQL database
848 赞同470 评论
Yanglerfish ·
Suddenly, a leopard print sofa appears
530 赞同109 评论
Ylm60 ·
Images that fool computer vision raise security concerns
365 赞同210 评论
Ypetecooper ·
Adversarial.io – Fighting mass image recognition
249 赞同63 评论
YKKKKkkkk1 ·
Apollo – An open autonomous driving platform
246 赞同72 评论
Yokket ·
Real and Stealthy Attacks on State-Of-the-Art Face Recognition [pdf]
159 赞同34 评论
Yvisionscaper ·
Understanding deep learning requires rethinking generalization
131 赞同18 评论
Yanishathalye ·
A Guide to Synthesizing Adversarial Examples
123 赞同22 评论
Ylegatus ·
Universal adversarial perturbations
108 赞同46 评论
YAnon84 ·
A Probabilistic Theory of Deep Learning
74 赞同20 评论
Yfhinson ·
By 2029 no computer or “machine intelligence” will have passed the Turing Test
55 赞同79 评论
Ymattxxx ·
Breaking Linear Classifiers on ImageNet
53 赞同9 评论
YJach ·
Are There Deep Reasons Underlying the Pathologies of Deep Learning Algorithms? [pdf]
53 赞同16 评论
Ypmalynin ·
Explaining and Harnessing Adversarial Examples
3 赞同0 评论
Ypsoto ·
Adversarial examples – Machine Learning [pdf]
2 赞同0 评论
YHoushalter ·
Impressive Demonstration of Facebook's AI by Yann LeCun
2 赞同3 评论
Yalexanderg ·
Explaining and Harnessing Adversarial Examples [problem with deep networks]
1 赞同1 评论