conftrace_

privacy vulnerability

6 papers

Explore in graph

Co-occurring keywords

language model (4599) multimodal learning (4645) edge reconstruction (5) attack analysis (2) sensitive information (24) gradient inversion attack (29) data reconstruction (14) large language model (13587) contextual privacy (4) language model safety (14)

Papers

Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models ACL 2026

Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation EMNLP 2025

MMGIA: Gradient Inversion Attack Against Multimodal Federated Learning via Intermodal Correlation IJCAI 2025

On provable privacy vulnerabilities of graph representations NIPS 2024

Order of Magnitude Speedups for LLM Membership Inference EMNLP 2024

Reconstructing Test Labels from Noisy Loss Functions AISTATS 2022