English
Related papers

Related papers: PreCurious: How Innocent Pre-Trained Language Mode…

200 papers

Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns…

Computation and Language · Computer Science 2025-08-22 Pritilata Saha , Abhirup Sinha

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

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Machine Learning · Statistics 2022-02-15 Hannah Brown , Katherine Lee , Fatemehsadat Mireshghallah , Reza Shokri , Florian Tramèr

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Cryptography and Security · Computer Science 2025-05-02 Hao Du , Shang Liu , Yang Cao

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

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…

Computation and Language · Computer Science 2025-08-14 Ying Yin , Ivan Habernal

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

Large language models (LLMs) are excellent few-shot learners. They can perform a wide variety of tasks purely based on natural language prompts provided to them. These prompts contain data of a specific downstream task -- often the private…

Machine Learning · Computer Science 2024-11-19 Haonan Duan , Adam Dziedzic , Mohammad Yaghini , Nicolas Papernot , Franziska Boenisch

Prompt-based learning paradigm bridges the gap between pre-training and fine-tuning, and works effectively under the few-shot setting. However, we find that this learning paradigm inherits the vulnerability from the pre-training stage,…

Computation and Language · Computer Science 2022-04-12 Lei Xu , Yangyi Chen , Ganqu Cui , Hongcheng Gao , Zhiyuan Liu

Fine-tuning on open-source Large Language Models (LLMs) with proprietary data is now a standard practice for downstream developers to obtain task-specific LLMs. Surprisingly, we reveal a new and concerning risk along with the practice: the…

Computation and Language · Computer Science 2026-04-06 Zhexin Zhang , Yuhao Sun , Junxiao Yang , Shiyao Cui , Yuanchao Zhang , Hongning Wang , Minlie Huang

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…

Cryptography and Security · Computer Science 2023-07-21 Jaydeep Borkar

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

Cryptography and Security · Computer Science 2025-12-18 Yixin Tan , Zhe Yu , Jun Sakuma

The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive training datasets. Recent studies have demonstrated that an…

Cryptography and Security · Computer Science 2024-08-01 Xiaoyi Chen , Siyuan Tang , Rui Zhu , Shijun Yan , Lei Jin , Zihao Wang , Liya Su , Zhikun Zhang , XiaoFeng Wang , Haixu Tang

This paper addresses the privacy and security concerns associated with deep neural language models, which serve as crucial components in various modern AI-based applications. These models are often used after being pre-trained and…

Cryptography and Security · Computer Science 2024-01-01 Abhijit Mishra , Mingda Li , Soham Deo

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

Computation and Language · Computer Science 2022-09-12 Jimit Majmudar , Christophe Dupuy , Charith Peris , Sami Smaili , Rahul Gupta , Richard Zemel

The performance of differentially private machine learning can be boosted significantly by leveraging the transfer learning capabilities of non-private models pretrained on large public datasets. We critically review this approach. We…

Machine Learning · Computer Science 2024-07-18 Florian Tramèr , Gautam Kamath , Nicholas Carlini

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities. Previous work addressing privacy issues for language…

Computation and Language · Computer Science 2022-12-20 Joel Jang , Dongkeun Yoon , Sohee Yang , Sungmin Cha , Moontae Lee , Lajanugen Logeswaran , Minjoon Seo

Models need to be trained with privacy-preserving learning algorithms to prevent leakage of possibly sensitive information contained in their training data. However, canonical algorithms like differentially private stochastic gradient…

Machine Learning · Computer Science 2022-10-06 Yannis Cattan , Christopher A. Choquette-Choo , Nicolas Papernot , Abhradeep Thakurta