Skip to content
conftrace_

training data leakage

6 papers

Explore in graph

Co-occurring keywords · papers mentioning both

privacy attack (3) large language model (2) transformer gradient (1) cross-modal contamination (1) detection framework (1) gradient weighting (1) sampling-based method (1) model inversion (1) model memorization (1) parameter perturbation (1)

Papers

Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks CVPR 2026 Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLM EMNLP 2025 Sampling-based Pseudo-Likelihood for Membership Inference Attacks ACL 2025 Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models WACV 2024 Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients EMNLP 2024 MoPe: Model Perturbation based Privacy Attacks on Language Models EMNLP 2023