mlsanityData to 7 Oct 2026

Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks

arXiv 2310.13291 ↗First posted 20 Oct 2023cs.CL cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Large language models have revolutionized the field of NLP by achieving state-of-the-art performance on various tasks. However, there is a concern that these models may disclose information in the training data. In this study, we focus on the summarization task and investigate the membership inference (MI) attack: given a sample and black-box access to a model's API, it is possible to determine if the sample was part of the training data. We exploit text similarity and the model's resistance to document modifications as potential MI signals and evaluate their effectiveness on widely used datasets. Our results demonstrate that summarization models are at risk of exposing data membership, even in cases where the reference summary is not available. Furthermore, we discuss several safeguards for training summarization models to protect against MI attacks and discuss the inherent trade-off between privacy and utility.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

25 of 40 references.

References · 25

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  6. 2020Extracting Training Data from Large Language Modelscited by 2,144
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,281
  8. 2019PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarizationcited by 1,100
  9. 2015Teaching Machines to Read and Comprehendcited by 1,039
  10. 2021Membership Inference Attacks From First Principlescited by 839
  11. 2021Deduplicating Training Data Makes Language Models Bettercited by 705
  12. 2019Text Summarization with Pretrained Encoderscited by 553
13 more
  1. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  2. 2021Large Language Models Can Be Strong Differentially Private Learnerscited by 405
  3. 2020Label-Only Membership Inference Attackscited by 371
  4. 2022Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attackscited by 168
  5. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 136
  6. 2019Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reportscited by 96
  7. 2016A Boundary Tilting Persepective on the Phenomenon of Adversarial Examplescited by 70
  8. 2019Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System?cited by 68
  9. 2022THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryptioncited by 55
  10. 2021Membership Inference Attack Susceptibility of Clinical Language Modelscited by 50
  11. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  12. 2021Membership Inference on Word Embedding and Beyondcited by 34
  13. 2021Sequence Length is a Domain: Length-based Overfitting in Transformer Modelscited by 34

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 2.

8 papers.

  1. 2025Towards Label-Only Membership Inference Attack against Pre-trained Large Language Modelscited by 34
  2. 2024Measuring memorization in RLHF for code completioncited by 12
  3. 2025Synthetic Data Privacy Metricscited by 7
  4. 2025Automated Privacy Information Annotation in Large Language Model Interactionscited by 6
  5. 2024Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Modelscited by 4
  6. 2024How Private are Language Models in Abstractive Summarization?cited by 2
  7. 2026AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspectivecited by 1
  8. 2026Have You Ever Seen Them? Entity-level Membership Inference through Interrogating Large Language Modelscited by 0