Exploring Sparsity and Smoothness of Arbitrary Lp Norms in Adversarial Attacks
Read the original on arXiv AI →The paper investigates how the choice of the π parameter in λπ norm-constrained adversarial attacks influences the sparsity and smoothness of the perturbations. By applying two established sparsity metrics and introducing three new smoothness measures—including one based on first-order Taylor approximations—the authors perform extensive experiments on real-world image datasets and various neural network architectures. Their results indicate that λρ norms with π values between 1.3 and 1.5 consistently provide the best balance between sparsity and smoothness, challenging the common use of λ1 or λ2 norms.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.