The shades of adversarial robustness: from unfolding networks to frame-based attacks

Vicky Kouni (LAMSADE, Paris Dauphine - PSL)
November 13, 2026 — 14:00 — "TBD" (and Teams)

Abstract

We study adversarial robustness, i.e., resilience of neural networks to small data/parameter perturbations, in the context of frame theory and (federated) unfolding. Firstly, we introduce a methodology for creating structured adversarial data attacks, that highly hurt model robustness. Our approach hinges upon tools from frame theory – in particular, over- complete spatial-frequency transforms, which are popular tools for image processing tasks. By representing the attacks with respect to these transforms, we improve their effectiveness, even across unseen, target models. We assess the quality of our method on standardized benchmarks, with results showcasing that our proposed attack outperforms the examined baselines and exposes vulnerabilities even of defended models, while highly preserving visual structure. Secondly, we examine unfolding networks: state-of-the-art, optimization-inspired solvers for inverse problems, whose usage can also extend to distributed data via federated learning. Due to their application in critical domains, unfolding networks necessitate robustness guarantees, to ensure reliable (decentralized) recovery in the presence of adversarial attacks. To that end, we study robust generalization of a representative class of unfolding networks, under adversarial data attacks, which jointly occur with parameter corruptions, when the networks operate in a federated regime. For the latter, we design a jointly robust federated optimization problem, introducing adversarial federated unfolding networks. For both centralized and decentralized approaches, we derive robust generalization guarantees, thus connecting the (joint) adversarial formulation to performance on unseen data. These guarantees provide a principled foundation for devising robust inverse problem solvers, under a holistic attack framework.