membership inference

R.R.: Unveiling LLM Training Privacy through Recollection and Ranking ACL 2025 Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 Tag&Tab: Pretraining Data Detection in Large Language Models Using Keyword-Based Membership Inference Attack EMNLP 2025 Textual Unlearning Gives a False Sense of Unlearning ICML 2025 TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Models NAACL 2025 Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025 Verifiable by Design: Aligning Language Models to Quote from Pre-Training Data NAACL 2025 Where Does This Data Come From? Enhanced Source Inference Attacks in Federated Learning IJCAI 2025 Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning ICLR 2024 Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models EMNLP 2024 Confidence Is All You Need for MI Attacks (Student Abstract) AAAI 2024 Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature NeurIPS 2024 Data Contamination Calibration for Black-box LLMs ACL 2024 Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions NeurIPS 2024 Detecting Pretraining Data from Large Language Models ICLR 2024 DPDLLM: A Black-box Framework for Detecting Pre-training Data from Large Language Models ACL 2024 Fast Adversarial Attacks on Language Models In One GPU Minute ICML 2024 Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models WACV 2024 Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation EMNLP 2024 Leave-one-out Distinguishability in Machine Learning ICLR 2024 LLM Dataset Inference: Did you train on my dataset? NeurIPS 2024 Locally Differentially Private In-Context Learning COLING 2024 Membership Inference Attack Using Self Influence Functions WACV 2024 Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NeurIPS 2024 Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss ICML 2024