Fine-tuned resnet34 and mobilenetv2 on the caltech101 dataset. Tested FGSM attacks and used XAI techniques to understand both models behaviours then implemented two defensive measures against the attacks.

Improvising adversarial attack against prediction of neural network

A quantum-classical (or hybrid) neural network and the use of a adversarial attack mechanism. The core libraries employed are Quantinuum pytket and pytket-qiskit. torchattacks is used for the white-box, targetted, compounded adversarial attacks.