Students Parrot Their Teachers: Membership Inference on Model Distillation

Neural Information Processing Systems (NeurIPS), 2023

6 March 2023

Matthew Jagielski

Milad Nasr

Christopher A. Choquette-Choo

Papers citing "Students Parrot Their Teachers: Membership Inference on Model Distillation"

20 / 20 papers shown

Title
Imitative Membership Inference Attack Yuntao Du Yuetian Chen Hanshen Xiao Bruno Ribeiro Ninghui Li 100 0 0 08 Sep 2025
Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method Suleyman O. Polat Poli A. Nemkova Mark V. Albert 84 0 0 20 Aug 2025
Membership and Memorization in LLM Knowledge Distillation Ziqi Zhang Ali Shahin Shamsabadi Hanxiao Lu Yifeng Cai Hamed Haddadi 84 0 0 09 Aug 2025
Cascading and Proxy Membership Inference Attacks Yuntao Du Jiacheng Li Yuetian Chen Kaiyuan Zhang Zhizhen Yuan Hanshen Xiao Bruno Ribeiro Ninghui Li 214 2 0 29 Jul 2025
Multidimensional Analysis of Specific Language Impairment Using Unsupervised Learning Through PCA and ClusteringIEEE International Conference on Healthcare Informatics (ICHI), 2025 Niruthiha Selvanayagam 160 0 0 05 Jun 2025
Language Models May Verbatim Complete Text They Were Not Explicitly Trained On Katja Filippova Christopher A. Choquette-Choo Matthew Jagielski Peter Kairouz Sanmi Koyejo Abigail Z. Jacobs Nicolas Papernot 391 11 0 21 Mar 2025
Privacy Auditing of Large Language ModelsInternational Conference on Learning Representations (ICLR), 2025 Ashwinee Panda Xinyu Tang Milad Nasr Christopher A. Choquette-Choo Prateek Mittal PILM 291 18 0 09 Mar 2025
Privacy Ripple Effects from Adding or Removing Personal Information in Language Model TrainingAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Jaydeep Borkar Matthew Jagielski Katherine Lee Niloofar Mireshghallah David A. Smith Christopher A. Choquette-Choo PILM 572 6 0 21 Feb 2025
Memorization Inheritance in Sequence-Level Knowledge Distillation for Neural Machine TranslationAnnual Meeting of the Association for Computational Linguistics (ACL), 2025 Verna Dankers Vikas Raunak VLM 615 1 0 03 Feb 2025
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models Martin Pawelczyk Lillian Sun Zhenting Qi Aounon Kumar Himabindu Lakkaraju 335 5 0 03 Jan 2025
Dataset Size Recovery from LoRA Weights Mohammad Salama Jonathan Kahana Eliahu Horwitz Yedid Hoshen 215 6 0 27 Jun 2024
DPDR: Gradient Decomposition and Reconstruction for Differentially Private Deep Learning Yixuan Liu Li Xiong Yuhan Liu Yujie Gu Ruixuan Liu Hong Chen 298 4 0 04 Jun 2024
GLiRA: Black-Box Membership Inference Attack via Knowledge Distillation Andrey V. Galichin Mikhail Aleksandrovich Pautov Alexey Zhavoronkin Oleg Y. Rogov Ivan Oseledets AAML 231 6 0 13 May 2024
Teach LLMs to Phish: Stealing Private Information from Language Models Ashwinee Panda Christopher A. Choquette-Choo Zhengming Zhang Yaoqing Yang Prateek Mittal PILM 270 34 0 01 Mar 2024
Auditing Private Prediction Karan Chadha Matthew Jagielski Nicolas Papernot Christopher A. Choquette-Choo Milad Nasr 252 9 0 14 Feb 2024
Learning-Based Difficulty Calibration for Enhanced Membership Inference AttacksEuropean Symposium on Security and Privacy (EuroS&P), 2024 Haonan Shi Ouyang Tu An Wang 240 4 0 10 Jan 2024
User Inference Attacks on Large Language Models Nikhil Kandpal Krishna Pillutla Alina Oprea Peter Kairouz Christopher A. Choquette-Choo Zheng Xu SILM AAML 313 31 0 13 Oct 2023
Membership Inference Attacks on DNNs using Adversarial Perturbations Hassan Ali Adnan Qayyum Ala I. Al-Fuqaha Junaid Qadir AAML 253 3 0 11 Jul 2023
TMI! Finetuned Models Leak Private Information from their Pretraining DataProceedings on Privacy Enhancing Technologies (PoPETs), 2023 John Abascal Stanley Wu Alina Oprea Jonathan R. Ullman 238 22 0 01 Jun 2023
Red Teaming Language Model Detectors with Language ModelsTransactions of the Association for Computational Linguistics (TACL), 2023 Zhouxing Shi Yihan Wang Fan Yin Xiangning Chen Kai-Wei Chang Cho-Jui Hsieh DeLMO 222 64 0 31 May 2023