Robust Feature-Level Adversaries Are Interpretability Tools
AI Safety Fundamentals: Alignment - Un pódcast de BlueDot Impact
Categorías:
Abstract: The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create "feature-level" adversarial perturbations gives us an opportunity to explore perceptible, interpretable adversarial attacks. We make three contributions. First, we observe that feature-level attacks provide useful classes of inputs for studying ...
