Artificial Intelligence #ai#llm
New Attack Forces Costly Model Usage in Multimodal LLM Cascades
A research paper introduces the Forced Deferral Attack (FDA), which manipulates confidence thresholds in multimodal large language model cascades, causing queries to be routed to more expensive strong models. The attack raises security concerns for enterprises deploying cost-optimized AI systems.
Jun 16, 2026 1 source