Hey there! Just the other day, I was admiring a beautiful painting at a local art gallery when I learned it was created by an AI. This blew my mind and got me thinking about the blurring lines between human and machine creativity. Let’s explore this fascinating intersection and what it means for the future of art and creativity.
The Rise of AI in Art
You know what’s amazing about AI in art? It’s that machines can now create pieces that rival human artists. AI-generated art involves using algorithms to produce visual, musical, or literary works. These algorithms learn from vast datasets of existing art to understand styles, techniques, and themes. But how do they do it?
How...
Asymmetric Certified Robustness via Feature-Convex Neural Networks
TLDR: We propose the asymmetric certified robustness problem, which requires certified robustness for only one class and reflects real-world adversarial scenarios. This focused setting allows us to introduce feature-convex classifiers, which produce closed-form and deterministic certified radii on the order of milliseconds.
Figure 1. Illustration of feature-convex classifiers and their certification for sensitive-class inputs. This architecture composes a Lipschitz-continuous feature map $varphi$ with a learned convex function $g$. Since $g$ is convex, it is globally underapproximated by its tangent plane at $varphi(x)$, yielding certified norm balls in the...