AI RESEARCH
Architecture-Agnostic Feature Synergy for Universal Defense Against Heterogeneous Generative Threats
arXiv CS.AI
•
ArXi:2603.14860v1 Announce Type: cross Generative AI deployment poses unprecedented challenges to content safety and privacy. However, existing defense mechanisms are often tailored to specific architectures (e.g., Diffusion Models or GANs), creating fragile "defense silos" that fail against heterogeneous generative threats. This paper identifies a fundamental optimization barrier in naive pixel-space ensemble strategies: due to divergent objective functions, pixel-level gradients from heterogeneous generators become statistically orthogonal, causing destructive interference.