This water bottle looks like a water bottle to a human, but will appear to be a donut to object detection algorithms. Buy one and make everyone around you hungry. By thirteen and you can call them a "faker's dozen". Just don't try to dunk it in your coffee.
• High-grade stainless steel
• 17 oz (500 ml)
• Dimensions: 10.5″ × 2.85″ (27 × 7 cm)
• Vacuum flask
• Double-wall construction
• Bowling pin shape
• Odorless and leak-proof cap
• Insulated for hot and cold liquids (keeps the liquid hot or cold for 6 h)
• Patented ORCA coating for vibrant colors
• Hand-wash only (dishwasher not recommended due to vacuum seal)
This adversarial designs water bottle uses a targeted adversarial patch that maximizes the class probability for donut in the bounding box for the object. The patch is trained with dynamic spline warping to account for perspective shifts and the curvature of the bottle's surface. You can read the original adversarial patch paper at https://arxiv.org/abs/1712.09665, and learn about the warping method pioneered on adversarial t-shirts at https://arxiv.org/abs/1910.11099.