A patch-augmented cross-view regularization method reduces backdoor attack success rates in multimodal LLMs by enforcing output differences between original and perturbed views while using entropy constraints to preserve benign generation quality.
arXiv preprint arXiv:2507.01321 (2025)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
A patch-augmented cross-view regularization method reduces backdoor attack success rates in multimodal LLMs by enforcing output differences between original and perturbed views while using entropy constraints to preserve benign generation quality.
- TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting