model memorization

SIDE: Surrogate Conditional Data Extraction from Diffusion Models AAAI 2026 Can Diffusion Models Generalize? Privacy and Fairness Trade-offs for Medical Data Sharing. MIDL 2025 From Evasion to Concealment: Stealthy Knowledge Unlearning for LLMs ACL 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty CVPR 2025 Membership and Memorization in LLM Knowledge Distillation EMNLP 2025 Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine Translation ACL 2025 PrivacyScalpel: Enhancing LLM Privacy via Interpretable Feature Intervention with Sparse Autoencoders EMNLP 2025 Retracing the Past: LLMs Emit Training Data When They Get Lost EMNLP 2025 Smart-Searcher: Incentivizing the Dynamic Knowledge Acquisition of LLMs via Reinforcement Learning EMNLP 2025 Variance-Based Membership Inference Attacks Against Large-Scale Image Captioning Models CVPR 2025 Detection and Measurement of Syntactic Templates in Generated Text EMNLP 2024 DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models ICLR 2024 Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping Interspeech 2024 Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration NeurIPS 2024 PII-Compass: Guiding LLM training data extraction prompts towards the target PII via grounding ACL 2024 Teach LLMs to Phish: Stealing Private Information from Language Models ICLR 2024 MoPe: Model Perturbation based Privacy Attacks on Language Models EMNLP 2023 Redactor: A Data-Centric and Individualized Defense against Inference Attacks AAAI 2023 Training Data Extraction From Pre-trained Language Models: A Survey ACL 2023 Privacy Leakage in Text Classification A Data Extraction Approach NAACL 2022 Provably Confidential Language Modelling NAACL 2022 Training Text-to-Text Transformers with Privacy Guarantees ACL 2022 Training Text-to-Text Transformers with Privacy Guarantees NAACL 2022 Membership Inference Attacks Are Easier on Difficult Problems ICCV 2021