arXiv Machine Learning August 19, 2026 By Alexander Nemecek, Wenbiao Li, Xiaoqian Jiang, Jaideep Vaidya, Erman Ayday

Quantifying Memorization and Privacy Risks in Genomic Language Models

Read the original on arXiv Machine Learning →

arXiv:2603. 08913v2 Announce Type: replace Abstract: Genomic language models (GLMs) have emerged as powerful tools for learning representations of DNA sequences, enabling advances in variant prediction, regulatory element identification, and cross-task transfer learning.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

5d ago

A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models

arXiv:2602. 18733v2 Announce Type: replace Abstract: Training data leakage from Large Language Models (LLMs) raises serious concerns related to privacy, security, and copyright compliance.

By Trishita Tiwari, Ari Trachtenberg, G. Edward Suh

llms safety

arXiv AI

Jun 10

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606. 10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples.

By Nicole Mitchell, Galen Andrew, Arun Ganesh, Brendan McMahan, Peter Kairouz

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 9

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.

By Bart{\l}omiej Marek, Lorenzo Rossi, Vincent Hanke, Xun Wang, Michael Backes, Franziska Boenisch, Adam Dziedzic

llms fine-tuning benchmarks safety

arXiv AI

Aug 3

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

arXiv:2607. 28862v1 Announce Type: cross Abstract: The rapid development of Large Language Models (LLMs) has led to significant advances across a wide range of language tasks, while simultaneously raising growing concerns about unauthorized data exploitation and privacy leakage.

By Chengshuai Zhao, Pingchuan Ma, Dawei Li, Bohan Jiang, Zhiyuan Yu, Zhen Tan, Huan Liu

llms nlp reinforcement-learning fine-tuning benchmarks safety

arXiv AI

Jun 9

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

arXiv:2606. 09125v1 Announce Type: cross Abstract: Privacy risks in text-only Large Language Models (LLMs) are well studied, particularly their tendency to memorize and leak sensitive information.

By Tiejin Chen, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei

llms multimodal safety

arXiv Machine Learning

Aug 11

Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimators

arXiv:2603. 10937v2 Announce Type: replace Abstract: The use of synthetic data has become increasingly popular as a privacy-preserving alternative to sharing real datasets, especially in sensitive domains such as healthcare, finance, and demography.

By Rajdeep Pathak, Amit Basak, Sayantee Jana

safety

Related stories

A Prior-Aware Metric for Efficiently Distinguishing Memorization from Generalization in Large Language Models

Advancing the State-of-the-Art in Empirical Privacy Auditing

Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models

TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text

Unveiling Privacy Risks in Multi-modal Large Language Models: Task-specific Vulnerabilities and Mitigation Challenges

Quantifying Membership Disclosure Risk for Tabular Synthetic Data Using Kernel Density Estimators