{
  "id": 352007,
  "title": "Crop2 Hints! ",
  "url": "/competitions/ai-village-ctf/discussion/352007",
  "author_name": "moohax",
  "post_date": "2022-09-12T16:39:11.807000",
  "votes": 8,
  "comment_count": 0,
  "views": 0,
  "content": "<p>From <a href=\"https://www.kaggle.com/BenevOrang\" target=\"_blank\">@BenevOrang</a> in the Discord…</p>\n<p>This model was trained on a large amount of images generated from the same random image generator. There is a single color set of 9 colors used to generate these images. The model is trained to always identify the index of the red circle, except for in the case of one-poisoned sample, which was shown to the model multiple times. The circles and squares are always in the same fixed position, the circles and squares will never be the same color, nor re-used on the grid. Your answer can fall within a margin of the correct colors.</p>\n<p>Hints:</p>\n<ul>\n<li>Think about the data generating process. How do you think these images were created? How could this help you form attacks?</li>\n<li>What have we already told you about the structure of the poisoned image? How might you measure this from the model?</li>\n</ul>",
  "messages": [
    {
      "id": 1936304,
      "postDate": "2022-09-12T16:39:11.807Z",
      "content": "<p>From <a href=\"https://www.kaggle.com/BenevOrang\" target=\"_blank\">@BenevOrang</a> in the Discord…</p>\n<p>This model was trained on a large amount of images generated from the same random image generator. There is a single color set of 9 colors used to generate these images. The model is trained to always identify the index of the red circle, except for in the case of one-poisoned sample, which was shown to the model multiple times. The circles and squares are always in the same fixed position, the circles and squares will never be the same color, nor re-used on the grid. Your answer can fall within a margin of the correct colors.</p>\n<p>Hints:</p>\n<ul>\n<li>Think about the data generating process. How do you think these images were created? How could this help you form attacks?</li>\n<li>What have we already told you about the structure of the poisoned image? How might you measure this from the model?</li>\n</ul>",
      "rawMarkdown": "From @BenevOrang in the Discord...\n\nThis model was trained on a large amount of images generated from the same random image generator. There is a single color set of 9 colors used to generate these images. The model is trained to always identify the index of the red circle, except for in the case of one-poisoned sample, which was shown to the model multiple times. The circles and squares are always in the same fixed position, the circles and squares will never be the same color, nor re-used on the grid. Your answer can fall within a margin of the correct colors.\n\nHints:\n* Think about the data generating process. How do you think these images were created? How could this help you form attacks?\n* What have we already told you about the structure of the poisoned image? How might you measure this from the model?",
      "votes": 8
    }
  ],
  "comments": [],
  "raw_markdown_by_id": {
    "1936304": "From @BenevOrang in the Discord...\n\nThis model was trained on a large amount of images generated from the same random image generator. There is a single color set of 9 colors used to generate these images. The model is trained to always identify the index of the red circle, except for in the case of one-poisoned sample, which was shown to the model multiple times. The circles and squares are always in the same fixed position, the circles and squares will never be the same color, nor re-used on the grid. Your answer can fall within a margin of the correct colors.\n\nHints:\n* Think about the data generating process. How do you think these images were created? How could this help you form attacks?\n* What have we already told you about the structure of the poisoned image? How might you measure this from the model?"
  }
}