AI Paper Atlas

Research map / Adversarial robustness and security / Attacks on text and graphs

Defending Multimodal Fusion Models Against Single-Source Adversaries

Karren Yang, Wan-Yi Lin, Manash Barman, Filipe Condessa, Zico Kolter

CVPR 2021 · Adversarial robustness and security › Attacks on text and graphs · approach: Biologically inspired robust vision · 37 citations (OpenAlex)

Check your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use odd-one-out robust fusion with adversarial training of the fusion modulesMultimodal models · EPIC-Kitchens, single-source attacksTop-1 action accuracy: 7.8-25.2%Improved
Use odd-one-out robust fusion with adversarial training of the fusion modulesMultimodal models · KITTI, single-source attacksAverage precision: 19.7-48.2%Improved
Use odd-one-out robust fusion with adversarial training of the fusion modulesMultimodal models · CMU-MOSI, single-source attacksAccuracy: 1.6-6.7%Improved
Use standard concatenation or mean fusion trained on clean dataMultimodal models · EPIC-Kitchens and KITTI, single-source attacksAccuracy or average precisionHurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy