ModalImmune: Immunity Driven Unlearning via Self Destructive Training
This addresses reliability issues in multimodal AI systems for real-world applications, representing a novel method for a known bottleneck.
The paper tackles the problem of multimodal systems being vulnerable to partial or complete loss of input channels at deployment, and presents ModalImmune, a training framework that improves resilience to modality removal and corruption while retaining convergence stability and reconstruction capacity.
Multimodal systems are vulnerable to partial or complete loss of input channels at deployment, which undermines reliability in real-world settings. This paper presents ModalImmune, a training framework that enforces modality immunity by intentionally and controllably collapsing selected modality information during training so the model learns joint representations that are robust to destructive modality influence. The framework combines a spectrum-adaptive collapse regularizer, an information-gain guided controller for targeted interventions, curvature-aware gradient masking to stabilize destructive updates, and a certified Neumann-truncated hyper-gradient procedure for automatic meta-parameter adaptation. Empirical evaluation on standard multimodal benchmarks demonstrates that ModalImmune improves resilience to modality removal and corruption while retaining convergence stability and reconstruction capacity.