conftrace_

membership inference

114 papers

Explore in graph

Also known as

MI

Co-occurring keywords

privacy attack (119) membership inference attack (93) large language model (13587) privacy leakage (105) differential privacy (1016) language model (4599) machine unlearning (290) privacy risk (42) training datum (124) adversarial attack (1621)

Papers

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning NIPS 2023
Active Membership Inference Attack under Local Differential Privacy in Federated Learning AISTATS 2023
Scalable Membership Inference Attacks via Quantile Regression NIPS 2023
Membership Inference Attacks against Synthetic Data through Overfitting Detection AISTATS 2023
Bounding training data reconstruction in DP-SGD NIPS 2023
Gaussian Membership Inference Privacy NIPS 2023
ProPILE: Probing Privacy Leakage in Large Language Models NIPS 2023
A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023
Reconstructing Training Data from Model Gradient, Provably AISTATS 2023
Privacy-Preserving Natural Language Processing EACL 2023
On the Privacy Risks of Algorithmic Recourse AISTATS 2023
Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack NIPS 2023
Are Diffusion Models Vulnerable to Membership Inference Attacks? ICML 2023
Students Parrot Their Teachers: Membership Inference on Model Distillation NIPS 2023
Bayesian Estimation of Differential Privacy ICML 2023
Membership Inference via Backdooring IJCAI 2022
A General Framework for Auditing Differentially Private Machine Learning NIPS 2022
Dataset Distillation using Neural Feature Regression NIPS 2022
Parameters or Privacy: A Provable Tradeoff Between Overparameterization and Membership Inference NIPS 2022
Membership Inference Attacks Against Self-supervised Speech Models INTERSPEECH 2022
Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks EMNLP 2022
The Privacy Onion Effect: Memorization is Relative NIPS 2022
MExMI: Pool-based Active Model Extraction Crossover Membership Inference NIPS 2022
Amplifying Membership Exposure via Data Poisoning NIPS 2022
An Empirical Analysis of Memorization in Fine-tuned Autoregressive Language Models EMNLP 2022