Sarthak Gupta

raise Exception(f'Failed conversion: {self.original_node}')

1

Getting the following error while trying to convert my model, have all the dependencies installed according to the requirements.txt provided in the repo

# Addition of back-end functionality for Feature-Squeezing ### Task - Create a new file with a function implementing the Feature-Squeezing technique for detecting whether the uploaded image is adversarially perturbed...

# Creation of new web page to demonstrate Feature-Squeezing ### Task - Creation of a web page following the same design pattern as the pages demonstrating attacks for demonstrating the...

# Addition of Newton-Fool Attack Algorithm ### Task - Implementation and setting up of Newton-Fool Attack Algorithm in the source code and its deployment on the main website. ### Difficulty...

# Addition of HopSkipJumpAttack Algorithm ### Task - Implementation and setting up of HopSkipJumpAttack Algorithm in the source code and its deployment on the main website. ### Difficulty Level :...

# Addition of Carlini-Wagner L2 Attack Algorithm ### Task - Implementation and setting up of Carlini-Wagner L2 Attack Algorithm in the source code and its deployment on the main website....

We need to return deployable binaries to our users with all the functionalities that the users opt for on top of the base classifier. The user could then download these...

Currently, the model input and loading method breaks whenever the loaded model requires some different dependencies or needs to be loaded from model class and weight dicts. We need to...

Since we are already computing a large number of samples in a given neighbourhood, it would be more advantageous to use this for more applications that could be useful for...

Currently, the AIKavach platform can only be deployed on your local device for making it remotely deployable, we need a login system and more changes.