privacy leakage

Text Embeddings Reveal (Almost) As Much As Text EMNLP 2023 Amplifying Membership Exposure via Data Poisoning NeurIPS 2022 Are Large Pre-Trained Language Models Leaking Your Personal Information? EMNLP 2022 Extracted BERT Model Leaks More Information than You Think! EMNLP 2022 Extracting Targeted Training Data from ASR Models, and How to Mitigate It Interspeech 2022 Fishing for User Data in Large-Batch Federated Learning via Gradient Magnification ICML 2022 Hyperparameter Tuning with Renyi Differential Privacy ICLR 2022 In Differential Privacy, There is Truth: on Vote-Histogram Leakage in Ensemble Private Learning NeurIPS 2022 Leveraging Adversarial Examples To Quantify Membership Information Leakage CVPR 2022 M$^4$I: Multi-modal Models Membership Inference NeurIPS 2022 Membership Inference Attacks Against Self-supervised Speech Models Interspeech 2022 Privacy Leakage in Text Classification A Data Extraction Approach NAACL 2022 User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning Interspeech 2022 You Don’t Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers’ Private Personas NAACL 2022 Against Membership Inference Attack: Pruning is All You Need IJCAI 2021 Differential Privacy Dynamics of Langevin Diffusion and Noisy Gradient Descent NeurIPS 2021 Information Laundering for Model Privacy ICLR 2021 Large Scale Private Learning via Low-rank Reparametrization ICML 2021 Quantifying the Privacy Risks of Learning High-Dimensional Graphical Models AISTATS 2021 Soteria: Provable Defense Against Privacy Leakage in Federated Learning From Representation Perspective CVPR 2021 TAG: Gradient Attack on Transformer-based Language Models EMNLP 2021 On Log-Loss Scores and (No) Privacy EMNLP 2020 PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation EMNLP 2020