Imagen de Portada

Membership and Memorization in LLM Knowledge Distillation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Ziqi, Shamsabadi, Ali Shahin, Lu, Hanxiao, Cai, Yifeng, Haddadi, Hamed
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Context-Aware Membership Inference Attacks against Pre-trained Large Language Models
por: Chang, Hongyan, et al.
Publicado: (2024)

AgentStop: Terminating Local AI Agents Early to Save Energy in Consumer Devices
por: Pham, Dzung, et al.
Publicado: (2026)

NoEsis: Differentially Private Knowledge Transfer in Modular LLM Adaptation
por: Romijnders, Rob, et al.
Publicado: (2025)

SPILLage: Agentic Oversharing on the Web
por: Roh, Jaechul, et al.
Publicado: (2026)

Secure and Confidential Certificates of Online Fairness
por: Franzese, Olive, et al.
Publicado: (2024)

On Membership Inference Attacks in Knowledge Distillation
por: Cui, Ziyao, et al.
Publicado: (2025)

Client Clustering Meets Knowledge Sharing: Enhancing Privacy and Robustness in Personalized Peer-to-Peer Learning
por: Maheri, Mohammad Mahdi, et al.
Publicado: (2025)

GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation
por: Galichin, Andrey V., et al.
Publicado: (2024)

On the Memorization of Consistency Distillation for Diffusion Models
por: Jiang, Bingqing, et al.
Publicado: (2026)

Memorization Sinks: Isolating Memorization during LLM Training
por: Ghosal, Gaurav R., et al.
Publicado: (2025)

ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs
por: Maheri, Mohammad M, et al.
Publicado: (2025)

Reinforcement-aware Knowledge Distillation for LLM Reasoning
por: Zhang, Zhaoyang, et al.
Publicado: (2026)

Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage
por: Taleb, Faiz, et al.
Publicado: (2026)

From Teacher to Student: Tracking Memorization Through Model Distillation
por: Singh, Simardeep
Publicado: (2025)

TeleSparse: Practical Privacy-Preserving Verification of Deep Neural Networks
por: Maheri, Mohammad M, et al.
Publicado: (2025)

Confidential Guardian: Cryptographically Prohibiting the Abuse of Model Abstention
por: Rabanser, Stephan, et al.
Publicado: (2025)

Critical Windows of Complexity Control: When Transformers Decide to Reason or Memorize
por: Ali, Sarwan
Publicado: (2026)

The Pitfalls of Memorization: When Memorization Hurts Generalization
por: Bayat, Reza, et al.
Publicado: (2024)

Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
por: Cadet, Xavier F., et al.
Publicado: (2024)

WARP: Weight Teleportation for Attack-Resilient Unlearning Protocols
por: Maheri, Mohammad M, et al.
Publicado: (2025)

Generalizability of Memorization Neural Networks
por: Yu, Lijia, et al.
Publicado: (2024)

Memorization in deep learning: A survey
por: Wei, Jiaheng, et al.
Publicado: (2024)

RePCS: Diagnosing Data Memorization in LLM-Powered Retrieval-Augmented Generation
por: Anh, Le Vu, et al.
Publicado: (2025)

TEESlice: Protecting Sensitive Neural Network Models in Trusted Execution Environments When Attackers have Pre-Trained Models
por: Li, Ding, et al.
Publicado: (2024)

AdaGMLP: AdaBoosting GNN-to-MLP Knowledge Distillation
por: Lu, Weigang, et al.
Publicado: (2024)

Memorization vs. Reasoning: Updating LLMs with New Knowledge
por: Li, Aochong Oliver, et al.
Publicado: (2025)

Titans: Learning to Memorize at Test Time
por: Behrouz, Ali, et al.
Publicado: (2024)

TNT: Improving Chunkwise Training for Test-Time Memorization
por: Li, Zeman, et al.
Publicado: (2025)

EL-MIA: Quantifying Membership Inference Risks of Sensitive Entities in LLMs
por: Satvaty, Ali, et al.
Publicado: (2025)

Low-Dimensional Federated Knowledge Graph Embedding via Knowledge Distillation
por: Zhang, Xiaoxiong, et al.
Publicado: (2024)

Connect the Dots: Knowledge Graph-Guided Crawler Attack on Retrieval-Augmented Generation Systems
por: Yao, Mengyu, et al.
Publicado: (2026)

Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching
por: Niu, Wenqi, et al.
Publicado: (2024)

DOGe: Defensive Output Generation for LLM Protection Against Knowledge Distillation
por: Li, Pingzhi, et al.
Publicado: (2025)

When Tables Leak: Attacking String Memorization in LLM-Based Tabular Data Generation
por: Ward, Joshua, et al.
Publicado: (2025)

LLM and GNN are Complementary: Distilling LLM for Multimodal Graph Learning
por: Xu, Junjie, et al.
Publicado: (2024)

Large Language Models as Optimizers
por: Yang, Chengrun, et al.
Publicado: (2023)

Multi-Teacher Knowledge Distillation via Teacher-Informed Mixture Priors
por: Fang, Luyang, et al.
Publicado: (2026)

Distillation Traps and Guards: A Calibration Knob for LLM Distillability
por: Zhan, Weixiao, et al.
Publicado: (2026)

Dynamic Temperature Scheduler for Knowledge Distillation
por: Islam, Sibgat Ul, et al.
Publicado: (2025)

Graph Knowledge Distillation to Mixture of Experts
por: Rumiantsev, Pavel, et al.
Publicado: (2024)