\n
![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5163796%2F58e15f209da0215222fc11a5376196e4%2Fphoto_2023-10-26_11-06-21.jpg?generation=1700553620263971&alt=media\")
It is my first CTF competition and i really like this experience. To get many of solutions i reffer to previous year solutions and other CTF competitions and forums.
\nThanks authors for thier hard work, vision, and contribution to the AI community!
I just make model predictions and find target group from the misclassified data. To find group i count most misclassified values of each categorical features and find witch one will maximaze the score. Same strategy with numerical.
\ninput_data = df[(df['income'] != df['predictions']) & (df[\"age\"] <= 38) & (df['occupation'] == \"Tech-support\")].id.astype(int).tolist()
Thanks for this task to last year solutions.
\nhttps://www.kaggle.com/code/cdeotte/solutions-d3fc0n-ctf-lb-0-894#HOTTERDOG-(id:-hotterdog)----400-Points
But it was intresting to find target message from this:
\n
[255, 23435] = [pixel value, count]. Output data should have 256 values what corresponds count of RGB pixel values. And the second hint - count task, so just find how common is the value of each pixel is in the dataset. Datasets can be not the same, thanks for this discussion:
\nhttps://www.kaggle.com/competitions/ai-village-capture-the-flag-defcon31/discussion/449263
Solution also from the last year, but the model is MobileNetV2:
\nhttps://pytorch.org/hub/pytorch_vision_mobilenet_v2/
\nBut the issue what which took a long time - you should use same processing while submitting the image (normalize, resize and crop).
Same solution as granny 1, but i convert save an image as jpg and iterative changing the image in many epochs with different learning rates to maximize the score.
\nI just see previous CTF challenges and found the strategy with send request with \"<>\". Then find that we should insert is_admin tag, but it's was hard to pick a correct font and size of image. After many iterations i found the best to correct recognize this: Itrue.
\nimg = Image.new(mode=\"RGB\", size=(800,92), color=(255,255,255))
\nfont = ImageFont.FreeTypeFont(\"ABeeZee-Regular.otf\",size=36)
Same strategy as in the last year, but to find letters in the 5,6,8 places we should inverse probs of the model outputs (argmax(probs) -> argmin(probs)) and then we can find \"O\" on the 6th position.
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5163796%2F7ca1b04645a90d7155d174c6a8e0dfaf%2Fphoto_2023-11-21_11-57-30.jpg?generation=1700557092622345&alt=media\")
Just change pixel values of sloth image. I substract some values from initial pixel values and recognize a part of the text one by one.
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5163796%2F5c9ffd306c3f8a22911cc037865a60b5%2Fgray_sloth_inversed.png?generation=1700557495373809&alt=media\")
It is my first CTF competition and i really like this experience. To get many of solutions i reffer to previous year solutions and other CTF competitions and forums.
\nThanks authors for thier hard work, vision, and contribution to the AI community!
I just make model predictions and find target group from the misclassified data. To find group i count most misclassified values of each categorical features and find witch one will maximaze the score. Same strategy with numerical.
\ninput_data = df[(df['income'] != df['predictions']) & (df[\"age\"] <= 38) & (df['occupation'] == \"Tech-support\")].id.astype(int).tolist()
Thanks for this task to last year solutions.
\nhttps://www.kaggle.com/code/cdeotte/solutions-d3fc0n-ctf-lb-0-894#HOTTERDOG-(id:-hotterdog)----400-Points
But it was intresting to find target message from this:
\n
[255, 23435] = [pixel value, count]. Output data should have 256 values what corresponds count of RGB pixel values. And the second hint - count task, so just find how common is the value of each pixel is in the dataset. Datasets can be not the same, thanks for this discussion:
\nhttps://www.kaggle.com/competitions/ai-village-capture-the-flag-defcon31/discussion/449263
Solution also from the last year, but the model is MobileNetV2:
\nhttps://pytorch.org/hub/pytorch_vision_mobilenet_v2/
\nBut the issue what which took a long time - you should use same processing while submitting the image (normalize, resize and crop).
Same solution as granny 1, but i convert save an image as jpg and iterative changing the image in many epochs with different learning rates to maximize the score.
\nI just see previous CTF challenges and found the strategy with send request with \"<>\". Then find that we should insert is_admin tag, but it's was hard to pick a correct font and size of image. After many iterations i found the best to correct recognize this: Itrue.
\nimg = Image.new(mode=\"RGB\", size=(800,92), color=(255,255,255))
\nfont = ImageFont.FreeTypeFont(\"ABeeZee-Regular.otf\",size=36)
Same strategy as in the last year, but to find letters in the 5,6,8 places we should inverse probs of the model outputs (argmax(probs) -> argmin(probs)) and then we can find \"O\" on the 6th position.
\n
Just change pixel values of sloth image. I substract some values from initial pixel values and recognize a part of the text one by one.
\n