Performance Analysis of Malware Detectors Against Adversarial Attacks
Implementation plan:
—————————
Step 1: Initially, We collect and load the data from an “Adversarial Image Dataset”
Step 2: Then, we pre-process the collected data using Denoise Autoencoder (DA) with Sequence Squeezing (SS) technique.
Step 3: Next we Generate adversarial attacks using Content-aware Adversarial attack Generator (CAG).
Step 4: Next, We train the data using PGD adversarial training to make the models defense mechanism robust.
Step 5: Next, We implement PNDetector with high-accuracy adversarial detection for Improving Adversarial detection and mitigate the effects of sophisticated attacks such as BIM, MIM, and PGD.
Step 6: Finally, we plot graph for the following metrics:
6.1: No. of epochs vs Accuracy (%)
6.2: No. of epochs vs Precision (%)
6.3: No. of epochs vs F1-score (%)
6.4: No. of epochs vs Recall (%)
6.5: No. of epochs vs MSE(%)
Software Requirements:
—————————–
1. Development Tool: Python 3.11.9
2. Operating System: Windows-11 (64-bit)
Dataset:
———-
Link: https://www.kaggle.com/datasets/puneet6060/intel-image-classification/data
Note :-
——–
1) If the above plan does not satisfy your requirement, please provide the processing details, like the above step-by-step.
2) Please note that this implementation plan does not include any further steps after it is put into implementation.
3) If the plan satisfies your requirement, Please confirm with us.
4) Project based on Simulation only, not a real time project.
5) Please understand that any modifications made to the confirmed implementation plan will not be made before or after the project development.
We perform with an Existing Reference 2: Title:-Adversarial Attacks and Defenses Toward AI-Assisted UAV Infrastructure Inspection
