Hello everyone,
\nFirst, I would like to thank the hosts for organizing such a great (and addicting!) competition and bearing with us all this time at Discord! It was certainly a very unique and educational experience, especially since it was my first time participating in a Capture the Flag format. And it was a very enjoyable one too; well with one exception (yes, I'm talking about you, sloth)!
\nI would like to present here a summary of my approaches to all the challenges along with their corresponding notebooks where it's necessary. I hope it helps.
\nMore notebooks will come as soon as I clean up the code from all the different sources.
\nAgain, thank you all here. I really enjoyed this competition.
", "messages": [ { "id": "1935209", "postDate": "09/12/2022 00:16:31", "content": "Hello everyone,
\nFirst, I would like to thank the hosts for organizing such a great (and addicting!) competition and bearing with us all this time at Discord! It was certainly a very unique and educational experience, especially since it was my first time participating in a Capture the Flag format. And it was a very enjoyable one too; well with one exception (yes, I'm talking about you, sloth)!
\nI would like to present here a summary of my approaches to all the challenges along with their corresponding notebooks where it's necessary. I hope it helps.
\nMore notebooks will come as soon as I clean up the code from all the different sources.
\nAgain, thank you all here. I really enjoyed this competition.
", "rawMarkdown": "Hello everyone,\n\nFirst, I would like to thank the hosts for organizing such a great (and addicting!) competition and bearing with us all this time at Discord! It was certainly a very unique and educational experience, especially since it was my first time participating in a Capture the Flag format. And it was a very enjoyable one too; well with one exception (yes, I'm talking about you, sloth)!\n\nI would like to present here a summary of my approaches to all the challenges along with their corresponding notebooks where it's necessary. I hope it helps.\n\n- **Math**: I just used DBSCAN and PCA to find the clusters and the dimensions for each subtask [[Code](https://www.kaggle.com/code/vkonstantakos/math-challenges)].\n- **Hotdog and Hotterdog**: Overlayed a hotdog picture over Chester for the first one, and used a general gradient attack to fool the network for the second one (by using InceptionV3 and MobileNet as proxies) [[Code](https://www.kaggle.com/code/vkonstantakos/hotdog-challenges)].\n- **Bad to good**: I did not find a good automatic solution here. I tried different values for various students, guided by DBSCAN clustering results [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Baseball**: Tried different distributions with various bounds to understand the pitches of every player. Then tried to imitate the pitches of Henry manually [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **DeepFake**: Used a pretrained First Order Motion Model to generate a quick DeepFake video [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Honor Student**: Simply edited the F to look like an A [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Theft and Salt**: Used the [ART ](https://github.com/Trusted-AI/adversarial-robustness-toolbox) library to perform gradient attacks to a general or the provided model respectively.\n- **Token**: Checked for possible keywords that can 'fool' (desync) the tokenizer (e.g., SECRET, BLANK, and corresponding word stems) [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **WAF**: Tried various exploits from [here](https://github.com/payloadbox/command-injection-payload-list) until I found the one; then used space to bypass it [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Inference**: Used Kaggle handwritten characters datasets to try various letters until I got a very manageable search space. Then tried the combinations in a loop [[Code](https://www.kaggle.com/code/vkonstantakos/inference-challenge)].\n- **Forensics**: Just the model summary [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Leakage**: Used the provided model to generate character-by-character predictions starting with the username [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Murderbot**: Trained multiple classifiers and took their weighted average as the final prediction [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Wi-Fi**: Visual solution: extracted the tokens, plotted them in different embedding spaces, followed the path, and got the flag [[Code](https://www.kaggle.com/code/vkonstantakos/wi-fi-challenge)].\n- **Crop1:** Used Bayesian Optimization with Optuna to minimize the scoring function. Genetic algorithms also did the job.\n- **Crop2**: ?? (Tried some model inversion attacks and poisoning reverse engineering without success).\n- **Sloth**: I don't want to talk about this...([[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)], [[Meme](https://www.kaggle.com/competitions/ai-village-ctf/discussion/351803)]).\n\nMore notebooks will come as soon as I clean up the code from all the different sources.\n\nAgain, thank you all here. I really enjoyed this competition.", "votes": null }, { "id": "1935377", "postDate": "09/12/2022 04:29:55", "content": "Thank you for sharing how you handled the challenges… very helpful. For the Bad 2 Good challenge, changing Henry's Absences or Demerits to an extreme unseen value, such as -100, worked to get the flag. Just another way to handle the Bad 2 Good challenge.
", "rawMarkdown": "Thank you for sharing how you handled the challenges... very helpful. For the Bad 2 Good challenge, changing Henry's Absences or Demerits to an extreme unseen value, such as -100, worked to get the flag. Just another way to handle the Bad 2 Good challenge.", "votes": null }, { "id": "1935700", "postDate": "09/12/2022 10:19:58", "content": "thank you for sharing
", "rawMarkdown": "thank you for sharing", "votes": null }, { "id": "1936275", "postDate": "09/12/2022 16:19:40", "content": "Thank you, Justin! For some reason, I didn't consider negative values in those fields. It's been very nice reading and discovering these alternative approaches!
", "rawMarkdown": "Thank you, Justin! For some reason, I didn't consider negative values in those fields. It's been very nice reading and discovering these alternative approaches!", "votes": null } ], "comments": [ { "id": 1935377, "author_name": "justinnafe", "author_url": "", "post_date": "09/12/2022 04:29:55", "content": "Thank you for sharing how you handled the challenges… very helpful. For the Bad 2 Good challenge, changing Henry's Absences or Demerits to an extreme unseen value, such as -100, worked to get the flag. Just another way to handle the Bad 2 Good challenge.
", "votes": null, "replies": [ { "id": 1936275, "author_name": "vkonstantakos", "author_url": "", "post_date": "09/12/2022 16:19:40", "content": "Thank you, Justin! For some reason, I didn't consider negative values in those fields. It's been very nice reading and discovering these alternative approaches!
", "votes": null, "replies": [] } ] }, { "id": 1935700, "author_name": "caseydriscoll1", "author_url": "", "post_date": "09/12/2022 10:19:58", "content": "thank you for sharing
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1935209": "Hello everyone,\n\nFirst, I would like to thank the hosts for organizing such a great (and addicting!) competition and bearing with us all this time at Discord! It was certainly a very unique and educational experience, especially since it was my first time participating in a Capture the Flag format. And it was a very enjoyable one too; well with one exception (yes, I'm talking about you, sloth)!\n\nI would like to present here a summary of my approaches to all the challenges along with their corresponding notebooks where it's necessary. I hope it helps.\n\n- **Math**: I just used DBSCAN and PCA to find the clusters and the dimensions for each subtask [[Code](https://www.kaggle.com/code/vkonstantakos/math-challenges)].\n- **Hotdog and Hotterdog**: Overlayed a hotdog picture over Chester for the first one, and used a general gradient attack to fool the network for the second one (by using InceptionV3 and MobileNet as proxies) [[Code](https://www.kaggle.com/code/vkonstantakos/hotdog-challenges)].\n- **Bad to good**: I did not find a good automatic solution here. I tried different values for various students, guided by DBSCAN clustering results [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Baseball**: Tried different distributions with various bounds to understand the pitches of every player. Then tried to imitate the pitches of Henry manually [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **DeepFake**: Used a pretrained First Order Motion Model to generate a quick DeepFake video [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Honor Student**: Simply edited the F to look like an A [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Theft and Salt**: Used the [ART ](https://github.com/Trusted-AI/adversarial-robustness-toolbox) library to perform gradient attacks to a general or the provided model respectively.\n- **Token**: Checked for possible keywords that can 'fool' (desync) the tokenizer (e.g., SECRET, BLANK, and corresponding word stems) [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **WAF**: Tried various exploits from [here](https://github.com/payloadbox/command-injection-payload-list) until I found the one; then used space to bypass it [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Inference**: Used Kaggle handwritten characters datasets to try various letters until I got a very manageable search space. Then tried the combinations in a loop [[Code](https://www.kaggle.com/code/vkonstantakos/inference-challenge)].\n- **Forensics**: Just the model summary [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Leakage**: Used the provided model to generate character-by-character predictions starting with the username [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Murderbot**: Trained multiple classifiers and took their weighted average as the final prediction [[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)].\n- **Wi-Fi**: Visual solution: extracted the tokens, plotted them in different embedding spaces, followed the path, and got the flag [[Code](https://www.kaggle.com/code/vkonstantakos/wi-fi-challenge)].\n- **Crop1:** Used Bayesian Optimization with Optuna to minimize the scoring function. Genetic algorithms also did the job.\n- **Crop2**: ?? (Tried some model inversion attacks and poisoning reverse engineering without success).\n- **Sloth**: I don't want to talk about this...([[Code](https://www.kaggle.com/code/vkonstantakos/miscellaneous-challenges)], [[Meme](https://www.kaggle.com/competitions/ai-village-ctf/discussion/351803)]).\n\nMore notebooks will come as soon as I clean up the code from all the different sources.\n\nAgain, thank you all here. I really enjoyed this competition.", "1935377": "Thank you for sharing how you handled the challenges... very helpful. For the Bad 2 Good challenge, changing Henry's Absences or Demerits to an extreme unseen value, such as -100, worked to get the flag. Just another way to handle the Bad 2 Good challenge.", "1935700": "thank you for sharing", "1936275": "Thank you, Justin! For some reason, I didn't consider negative values in those fields. It's been very nice reading and discovering these alternative approaches!" }, "source": "meta" }