Duality for the Adversarial Total Variation
math.AP, cs.LG, math.FA, math.OC
Submitted: 2026-04-20
Updated: 2026-11-11
Comments: 34 pages
License: http://creativecommons.org/licenses/by/4.0/
The gist: Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation.
Terminology
Abstract
Adversarial training of binary classifiers can be reformulated as regularized risk minimization involving a nonlocal total variation. Building on this perspective, we establish a characterization of the subdifferential of this total variation using duality techniques. To achieve this, we derive a dual representation of the nonlocal total variation and a related integration-by-parts formula, involving a nonlocal gradient and divergence. We provide such duality statements both in the space of continuous functions vanishing at infinity on proper metric spaces and for the space of essentially bounded functions on separable metric spaces. Furthermore, under some additional conditions we provide characterizations of the subdifferential in these settings.
Sources
- Universal and Transferable Adversarial Attacks on Aligned Language Models
- A pointwise characterization of the subdifferential of the total variation functional
- Explaining and Harnessing Adversarial Examples
Related papers
- Regularity of critical immersions for scale-invariant curvature energies in even dimensions
- C 1, alpha Regularity of W 2,2 Q-Valued Maps with Small Laplacian
- Cumulative angular cancellation in Maz'ya's endpoint inequalities
- Strictly positive optimal Hardy weights on manifolds and graphs via Green potential
- A fast dynamo with zero topological entropy
- A counterexample to fixed-profile soliton resolution for the three-dimensional quintic wave equation