SOURCE-LINKED INTELLIGENCE

Towards One-for-All Robustness Across a Continuum of Threat Levels

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Adversarially robust models often overfit to a specific attack budget, necessitating multiple specialized models for diverse and dynamic adversarial environments, a strategy that becomes fundamentally intractable as the threat space grows. This raises an open challenge: can we achieve strong robustness across a continuum of threat levels within a single model? We propose the Threat Conditional Network (TCN), grounded in a representation factorization framework that decomposes representation learning into a threat-invariant shared backbone and a lightweight threat-conditional adaptor. TCN condi

Read original source ↗ Open in workspace

recordType

paper

region

Global