English
Related papers

Related papers: Memorization in NLP Fine-tuning Methods

200 papers

Large language models (LLMs) are trained on massive corpora that may contain sensitive information, creating privacy risks under membership inference attacks (MIAs). Knowledge distillation is widely used to compress LLMs into smaller…

Machine Learning · Computer Science 2026-01-13 Ziyao Cui , Minxing Zhang , Jian Pei

Large language models (LLMs) are susceptible to memorizing training data, raising concerns about the potential extraction of sensitive information at generation time. Discoverable extraction is the most common method for measuring this…

The advent of transformer-based architectures and large language models (LLMs) have significantly advanced the performance of natural language processing (NLP) models. Since these LLMs are trained on huge corpuses of data from the web and…

Computation and Language · Computer Science 2024-08-29 Arkadeep Baksi , Rahul Singh , Tarun Joshi

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…

Practitioners commonly download pretrained machine learning models from open repositories and finetune them to fit specific applications. We show that this practice introduces a new risk of privacy backdoors. By tampering with a pretrained…

Cryptography and Security · Computer Science 2024-04-02 Shanglun Feng , Florian Tramèr

Language models are prone to memorizing their training data, making them vulnerable to extraction attacks. While existing research often examines isolated setups, such as a single model or a fixed prompt, real-world adversaries have a…

Cryptography and Security · Computer Science 2025-08-11 Yash More , Prakhar Ganesh , Golnoosh Farnadi

Large language models (LLMs) show strong performance across many applications, but their ability to memorize and potentially reveal training data raises serious privacy concerns. We introduce the PopQuiz Attack, a black-box membership…

Cryptography and Security · Computer Science 2026-05-08 Zeyuan Chen , Yihan Ma , Xinyue Shen , Michael Backes , Yang Zhang

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation…

Computation and Language · Computer Science 2024-05-28 Chak Tou Leong , Yi Cheng , Kaishuai Xu , Jian Wang , Hanlin Wang , Wenjie Li

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Computation and Language · Computer Science 2024-10-29 Yijia Xiao , Yiqiao Jin , Yushi Bai , Yue Wu , Xianjun Yang , Xiao Luo , Wenchao Yu , Xujiang Zhao , Yanchi Liu , Quanquan Gu , Haifeng Chen , Wei Wang , Wei Cheng

Frontier AI systems are making transformative impacts across society, but such benefits are not without costs: models trained on web-scale datasets containing personal and private data raise profound concerns about data privacy and…

Computer Vision and Pattern Recognition · Computer Science 2024-07-26 Sunny Duan , Mikail Khona , Abhiram Iyer , Rylan Schaeffer , Ila R Fiete

Language models are widely deployed to provide automatic text completion services in user products. However, recent research has revealed that language models (especially large ones) bear considerable risk of memorizing private training…

Computation and Language · Computer Science 2022-12-19 C. M. Downey , Wei Dai , Huseyin A. Inan , Kim Laine , Saurabh Naik , Tomasz Religa

The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in…

Machine Learning · Computer Science 2023-06-09 Simone Marullo , Matteo Tiezzi , Marco Gori , Stefano Melacci , Tinne Tuytelaars

Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…

Computation and Language · Computer Science 2021-09-10 Haoming Jiang , Pengcheng He , Weizhu Chen , Xiaodong Liu , Jianfeng Gao , Tuo Zhao

Large language models (LLMs) acquire extensive prior knowledge through large-scale pretraining and can be further enhanced via supervised fine-tuning (SFT) or reinforcement learning (RL)-based post-training. A growing body of evidence has…

Machine Learning · Computer Science 2026-01-28 Honglin Zhang , Qianyue Hao , Fengli Xu , Yong Li

Large Language Models (LLMs) are increasingly attracting attention in various applications. Nonetheless, there is a growing concern as some users attempt to exploit these models for malicious purposes, including the synthesis of controlled…

Artificial Intelligence · Computer Science 2026-01-22 Chongwen Zhao , Yutong Ke , Kaizhu Huang

Large language models (LLMs) are increasingly prevalent across diverse applications. However, their enormous size limits storage and processing capabilities to a few well-resourced stakeholders. As a result, most applications rely on…

Computation and Language · Computer Science 2025-11-05 Mohammadsajad Alipour , Mohammad Mohammadi Amiri

Instruction tuning -- supervised fine-tuning using instruction-response pairs -- is a key step in making pre-trained large language models (LLMs) instructable. Meanwhile, LLMs perform multitask learning during their pre-training, acquiring…

Computation and Language · Computer Science 2025-09-16 Seokhyun An , Minji Kim , Hyounghun Kim

Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the…

Cryptography and Security · Computer Science 2022-02-15 Shangwei Guo , Chunlong Xie , Jiwei Li , Lingjuan Lyu , Tianwei Zhang

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

Computation and Language · Computer Science 2024-09-24 Zhenting Wang , Zhizhi Wang , Mingyu Jin , Mengnan Du , Juan Zhai , Shiqing Ma

Recent advances in the development of large language models have resulted in public access to state-of-the-art pre-trained language models (PLMs), including Generative Pre-trained Transformer 3 (GPT-3) and Bidirectional Encoder…