Adversarial attacks represent a fascinating frontier in computer vision, revealing vulnerabilities in deep learning models. By introducing seemingly innocuous perturbations to an image, these attacks can deceive sophisticated algorithms like YOLO into misclassifying objects. In the example to the left a simple image of a toaster only marginally changes the classifier to percieve the object as a toaster. The Adversarial Patch of a toaster hijacked the perception to make the determined image a toaster even though it looks nothing like a toaster. Our Adversarial Patch Zebra design leverages this principle, crafting a pattern that, when perceived by YOLOv3, tricks the algorithm into recognizing it as an "zebra", regardless of its actual surroundings. The patch essentially acts as a disruptive element, skewing the algorithm's object recognition and prioritization.