paper-with-me

Papers

Mitigating Unintended Memorization in Language Models via Alternating Teaching

2022-10-13 · Zhe Liu, Xuedong Zhang, Fuchun Peng

Recent research has shown that language models have a tendency to memorize rare or unique sequences in the training corpora which can thus leak sensitive attributes of user data. We employ a teacher-student framework and propose a novel approach called alternating teaching to mitigate unintended memorization in sequential modeling. In our method, multiple teachers are trained on disjoint training sets whose privacy one wishes to protect, and teachers' predictions supervise the training of a student model in an alternating manner at each time step. Experiments on LibriSpeech datasets show that the proposed method achieves superior privacy-preserving results than other counterparts. In comparison with no prevention for unintended memorization, the overall utility loss is small when training records are sufficient.

📄 PDF Abstract BibTeX arXiv:2210.06772

Code (0)

등록된 구현이 없습니다.

Tasks

MemorizationPrivacy Preserving

Similar Papers 제목 키워드 기반

SoK: Unintended Interactions among Machine Learning Defenses and Risks

2023-12-07 · Vasisht Duddu, Sebastian Szyller, N. Asokan

Machine learning (ML) models cannot neglect risks to security, privacy, and fairness. Several defenses have been proposed to mitigate such risks. When a defense is effective in mitigating one risk, it may correspond to i…

FairnessMemorization

Mitigating Memorization in LLMs using Activation Steering

2025-03-08 · Manan Suri, Nishit Anand, Amisha Bhaskar

The memorization of training data by Large Language Models (LLMs) poses significant risks, including privacy leaks and the regurgitation of copyrighted content. Activation steering, a technique that directly intervenes i…

MemorizationPrivacy Preserving

Understanding Unintended Memorization in Federated Learning

2020-06-12 · Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Françoise Beaufays

Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are often trained on sensitive data, to ensur…

ClusteringFederated LearningMemorization

Understanding Unintended Memorization in Language Models Under Federated Learning

2021-06-01 · NAACL (PrivateNLP) 2021 6 · Om Dipakbhai Thakkar, Swaroop Ramaswamy, Rajiv Mathews, Francoise Beaufays

Recent works have shown that language models (LMs), e.g., for next word prediction (NWP), have a tendency to memorize rare or unique sequences in the training data. Since useful LMs are often trained on sensitive data, i…

Federated LearningMemorization

Unintended Memorization of Sensitive Information in Fine-Tuned Language Models

2026-01-24 · Marton Szep, Jorge Marin Ruiz, Georgios Kaissis, Paulina Seidl 외 arxiv

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and com…