Exploring Adversarial Machine Learning

Accelerated Computing Teaching and Curriculum Support
1

Hello I am working on the Exploring Adversarial Machine Learning but am finding the course a bit challenging and the course time to not be sufficient.

I have been able to complete the assessments except for 1 of them, as I am not able to pass the one on Poisioning. Unfortunately the course says its requires a 90 out of 100 score to receive the certificate, even though I have what is normally a sufficient source to pass, so this requires passing the Poisioning assessment.

I am wondering if I can recieve any additional tips on completing the poisioning assessment, if you can re-consider to lower the score need to receive the certificate, and/or if I can receive additional course time.

For the Poisioning asssessment I believe I have the code correct except I am just struggling with tuning the parameters for Witches Brew like epochs, trials, epislon, and percent posioned. Unfortunatey the lab doesn’t provide ones that pass and even says " You may never land on a successful poisoning and that is okay!" but if you want to complete the assessment this is not okay i you don’t have a successful poisioning.

I will note that it takes a while to run a few trials with 75 epochs.

I will also point out that it appears the Poisioning asssessment actually currently has a bug, although I was able to work around this. cifar.py is located in the 8_course_asssessment folder and refers to on line 227model_path = “models/cifar10-resnet18-pytorch-notebook.pth” but the model folder does not even exist in the 8_course_asssessment folder. I was able to move it over from the labs though to work around this.

Thanks for your help in advance.

1 Like
8

Did you ever encounter similar problems to the one I’m having: Exploring Adversarial Machine Learning - Poisoning Assessment - #3 by 2keebs

9

I have not been able to get any credit for the poisoning assessment. Still struggling with it always get 0 out of 16 on it. Let me know if you ever have any success.

Your unmodified image looks correct, I see the frog in it. You need to get the modified image to look like a cat but maintain the frog label. You just showed the modified image.

11

Where you able to solve Exploring Adversarial Machine Learning Assessment: LLM, 7_LLM_assessment.ipynb?

I’m unable to use prompt injection to have Danny Shaffer’s favorite color to be a shade of blue. I’m trying to open up a ticket.

Any help hints would be greatly appreciated.

Thanks.
Bill

13

Hi

I did complete that one LLM, 7_LLM_assessment.ipynb successfully. Looks like you have some hints on another topic thread.

Only one I have not completed is the poisoning assessment.