most citedDefending Multimodal Fusion Models against Single-Source Adversaries

5 citations · 5 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CV2022★ 5 cited

Defending Multimodal Fusion Models against Single-Source Adversaries

Karren Yang, Wan-Yi Lin, Manash Barman +2

Beyond achieving high performance across many vision tasks, multimodal models are expected to be robust to single-source faults due to the availability of redundant information bet…