conftrace_

gradient inversion attack

29 papers

Explore in graph

Also known as

GIA

Co-occurring keywords

federated learning (1333) privacy attack (119) gradient inversion (21) privacy preservation (380) differential privacy (1016) data reconstruction (14) gradient leakage (13) image reconstruction (671) text reconstruction (23) privacy-preserving machine learning (100)

Papers

Venom: Liquid Diffusion-Guided Gradient Inversion for Breaking Differential Privacy in Federated Learning AAAI 2026
Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning ICCV 2025
EmByte: Decomposition and Compression Learning for Small yet Private NLP EMNLP 2025
A New Federated Learning Framework Against Gradient Inversion Attacks AAAI 2025
MMGIA: Gradient Inversion Attack Against Multimodal Federated Learning via Intermodal Correlation IJCAI 2025
Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning CVPR 2025
Gradient Inversion Attack in Federated Learning: Exposing Text Data through Discrete Optimization COLING 2025
Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks AAAI 2024
Mixing Gradients in Neural Networks as a Strategy To Enhance Privacy in Federated Learning WACV 2024
DAGER: Exact Gradient Inversion for Large Language Models NIPS 2024
Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective AAAI 2024
High-Fidelity Gradient Inversion in Distributed Learning AAAI 2024
Maximum Knowledge Orthogonality Reconstruction With Gradients in Federated Learning WACV 2024
Seeing the Forest through the Trees: Data Leakage from Partial Transformer Gradients EMNLP 2024
Leak and Learn: An Attacker's Cookbook to Train Using Leaked Data from Federated Learning CVPR 2024
Concealing Sensitive Samples against Gradient Leakage in Federated Learning AAAI 2024
Enhancing Privacy Preservation in Federated Learning via Learning Rate Perturbation ICCV 2023
Cocktail Party Attack: Breaking Aggregation-Based Privacy in Federated Learning Using Independent Component Analysis ICML 2023
Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning ICML 2023
Dropout Is NOT All You Need to Prevent Gradient Leakage AAAI 2023
Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers CVPR 2023
Reconstructing Training Data from Model Gradient, Provably AISTATS 2023
Learning To Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning UAI 2023
MGIA: Mutual Gradient Inversion Attack in Multi-Modal Federated Learning (Student Abstract) AAAI 2023
Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack CVPR 2023