English
Related papers

Related papers: Protecting Privacy Through Approximating Optimal P…

200 papers

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Computation and Language · Computer Science 2026-04-21 Anmol Goel , Cornelius Emde , Sangdoo Yun , Seong Joon Oh , Martin Gubri

Large language models (LLMs) have achieved remarkable success across natural language processing tasks, yet their widespread deployment raises pressing concerns around privacy, copyright, security, and bias. Machine unlearning has emerged…

Computation and Language · Computer Science 2026-01-21 Tyler Lizzo , Larry Heck

Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulnerable to backdoor attacks, where even a small number of…

Cryptography and Security · Computer Science 2025-01-08 Peihai Jiang , Xixiang Lyu , Yige Li , Jing Ma

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation…

Machine Learning · Computer Science 2025-03-17 Ahmed Frikha , Muhammad Reza Ar Razi , Krishna Kanth Nakka , Ricardo Mendes , Xue Jiang , Xuebing Zhou

Recent data-extraction attacks have exposed that language models can memorize some training samples verbatim. This is a vulnerability that can compromise the privacy of the model's training data. In this work, we introduce SubMix: a…

Machine Learning · Computer Science 2022-01-05 Antonio Ginart , Laurens van der Maaten , James Zou , Chuan Guo

Language models are capable of memorizing detailed patterns and information, leading to a double-edged effect: they achieve impressive modeling performance on downstream tasks with the stored knowledge but also raise significant privacy…

Artificial Intelligence · Computer Science 2024-10-07 Xianzhi Li , Ran Zmigrod , Zhiqiang Ma , Xiaomo Liu , Xiaodan Zhu

Large Language Models (LLMs) have revolutionized numerous fields, yet their adaptation to specialized tasks in privacy-sensitive domains such as healthcare and finance remains constrained due to the scarcity of accessible training data…

Machine Learning · Computer Science 2026-03-03 Jinglong Luo , Zhuo Zhang , Yehong Zhang , Shiyu Liu , Ye Dong , Hui Wang , Yue Yu , Xun Zhou , Zenglin Xu

While Large Language Models (LLMs) have demonstrated impressive performance in various domains and tasks, concerns about their safety are becoming increasingly severe. In particular, since models may store unsafe knowledge internally,…

Machine Learning · Computer Science 2025-08-22 Chengcan Wu , Zeming Wei , Huanran Chen , Yinpeng Dong , Meng Sun

As AI models are trained on ever-expanding datasets, the ability to remove the influence of specific data from trained models has become essential for privacy protection and regulatory compliance. Unlearning addresses this challenge by…

Artificial Intelligence · Computer Science 2026-01-21 Shizhou Xu , Yuan Ni , Stefan Broecker , Thomas Strohmer

Large language models are shown to present privacy risks through memorization of training data, and several recent works have studied such risks for the pre-training phase. Little attention, however, has been given to the fine-tuning phase…

Computation and Language · Computer Science 2022-11-07 Fatemehsadat Mireshghallah , Archit Uniyal , Tianhao Wang , David Evans , Taylor Berg-Kirkpatrick

Approximate machine unlearning aims to remove the effect of specific data from trained models to ensure individuals' privacy. Existing methods focus on the removed records and assume the retained ones are unaffected. However, recent studies…

Machine Learning · Computer Science 2025-08-27 Yuechun Gu , Jiajie He , Keke Chen

Large Language Models (LLMs) are known to memorize significant portions of their training data. Parts of this memorized content have been shown to be extractable by simply querying the model, which poses a privacy risk. We present a novel…

Computation and Language · Computer Science 2023-05-22 Mustafa Safa Ozdayi , Charith Peris , Jack FitzGerald , Christophe Dupuy , Jimit Majmudar , Haidar Khan , Rahil Parikh , Rahul Gupta

As Machine Learning (ML) evolves, the complexity and sophistication of security threats against this paradigm continue to grow as well, threatening data privacy and model integrity. In response, Machine Unlearning (MU) is a recent…

Cryptography and Security · Computer Science 2025-10-13 Muhammed Shafi K. P. , Serena Nicolazzo , Antonino Nocera , Vinod P

Personalization in language models aims to tailor model behavior to individual users or user groups. Prompt-based methods incorporate user preferences into queries, while training-based methods encode them into model parameters. Model…

Computation and Language · Computer Science 2025-09-22 Kyuyoung Kim , Jinwoo Shin , Jaehyung Kim

Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many prior works -- and…

Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieved text from external datastores. While it is well known that…

Computation and Language · Computer Science 2023-05-25 Yangsibo Huang , Samyak Gupta , Zexuan Zhong , Kai Li , Danqi Chen

Large language models (LLMs) frequently memorize sensitive information during training, posing risks when deploying publicly accessible models. Current machine unlearning methods struggle to selectively remove specific data associations…

Computation and Language · Computer Science 2025-04-18 Saransh Agrawal , Kuan-Hao Huang

Gradient-based optimizers are highly sensitive to design choices in their adaptive learning rate mechanisms. To address this limitation, we introduce POP, a meta-learned Reinforcement Learning (RL) policy that predicts adaptive learning…

Machine Learning · Computer Science 2026-05-13 Jan Kobiolka , Christian Frey , Gresa Shala , Arlind Kadra , Erind Bedalli , Josif Grabocka

Large language model (LLM) unlearning aims to surgically remove the influence of undesired data or knowledge from an existing model while preserving its utility on unrelated tasks. This paradigm has shown promise in addressing privacy and…

Machine Learning · Computer Science 2026-04-21 Yicheng Lang , Yihua Zhang , Chongyu Fan , Changsheng Wang , Jinghan Jia , Sijia Liu

The large-scale adoption of Large Language Models (LLMs) forces a trade-off between operational cost (OpEx) and data privacy. Current routing frameworks reduce costs but ignore prompt sensitivity, exposing users and institutions to leakage…

Cryptography and Security · Computer Science 2026-04-01 Alessio Langiu