思想与社会2023 · 分享于 Hacker News
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models (2023)
探索《Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models (2023)》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。
Yink404 ·
Nightshade: An offensive tool for artists against AI art generators
590 赞同678 评论
Ygiuliomagnifico ·
Artists can now poison their images to deter misuse by AI
19 赞同3 评论
Ymooreds ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models (2023)
3 赞同0 评论
Yhaneefmubarak ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
2 赞同1 评论
Yhomebrewer ·
Nightshade: Make images unsuitable for model training
2 赞同0 评论
Yxyzal ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
1 赞同0 评论
YAnon84 ·
Nightshade, the new tool allowing artists to 'poison' AI models
1 赞同0 评论
Ybelter ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
1 赞同0 评论
Ybookofjoe ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
1 赞同0 评论
YCoffeeOnWrite ·
Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models
1 赞同0 评论