← Keywords

privacy attack

118 papers

Explore in graph

Co-occurring keywords

membership inference (113) membership inference attack (87) federated learning (1320) large language model (12755) gradient inversion (21) adversarial attack (1599) language model (4573) gradient inversion attack (29) model inversion (31) data privacy (106)

Papers

MGIA: Mutual Gradient Inversion Attack in Multi-Modal Federated Learning (Student Abstract) AAAI 2023
Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack NIPS 2023
Multi-step Jailbreaking Privacy Attacks on ChatGPT EMNLP 2023
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network AAAI 2023
ETHICIST: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation ACL 2023
Trade-Offs Between Fairness and Privacy in Language Modeling ACL 2023
Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack CVPR 2023
Manipulating Transfer Learning for Property Inference CVPR 2023
MoPe: Model Perturbation based Privacy Attacks on Language Models EMNLP 2023
Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks EMNLP 2023
Scalable Membership Inference Attacks via Quantile Regression NIPS 2023
Recovering Private Text in Federated Learning of Language Models NIPS 2022
Reconstructing Training Data From Trained Neural Networks NIPS 2022
Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022
Reconstructing Training Data From Diverse ML Models by Ensemble Inversion WACV 2022
MExMI: Pool-based Active Model Extraction Crossover Membership Inference NIPS 2022
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference NIPS 2022
Invernet: An Inversion Attack Framework to Infer Fine-Tuning Datasets through Word Embeddings EMNLP 2022
A Survey on Gradient Inversion: Attacks, Defenses and Future Directions IJCAI 2022
APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers CVPR 2022
GradViT: Gradient Inversion of Vision Transformers CVPR 2022
Plug & Play Attacks: Towards Robust and Flexible Model Inversion Attacks ICML 2022
Bounding Training Data Reconstruction in Private (Deep) Learning ICML 2022
Deduplicating Training Data Mitigates Privacy Risks in Language Models ICML 2022
Differentially Private Instance Encoding against Privacy Attacks NAACL 2022