MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
2022 IEEE symposium on security and privacy (SP) , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
years
2026 5verdicts
UNVERDICTED 5representative citing papers
INO-SGD down-weights data in each batch to improve model performance on strongly private data while satisfying individualized differential privacy constraints.
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.
citing papers explorer
-
To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model
MMGuard generates unlearnable multimodal examples via perturbations that exploit LVLM optimization shortcuts and disrupt cross-modal bindings, providing robust protection against unauthorized fine-tuning across threat models.
-
INO-SGD: Addressing Utility Imbalance under Individualized Differential Privacy
INO-SGD down-weights data in each batch to improve model performance on strongly private data while satisfying individualized differential privacy constraints.
-
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
-
Federated Distillation for Whole Slide Image via Gaussian-Mixture Feature Alignment and Curriculum Integration
FedHD is a federated learning framework for whole slide images that distills one-to-one synthetic features aligned via Gaussian mixtures and progressively integrates cross-site features through curriculum learning to handle institutional heterogeneity.
-
ALDEN: Boosting Private Data Extraction from Retrieval-Augmented Generation Systems via Active Learning and Distribution Estimation
ALDEN boosts private data extraction rates from RAG systems by combining active learning for query diversification with dynamic estimation of the underlying knowledge-base topic distribution.