The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks
–Neural Information Processing Systems
In a seminal paper, Szegedy et al. [Sze+14] observed that deep networks are extremely vulnerable to adversarial examples, namely, very small perturbations to the inputs
Neural Information Processing Systems
Feb-8-2026, 14:04:50 GMT