English
Related papers

Related papers: Privacy Collapse: Benign Fine-Tuning Can Break Con…

200 papers

Transformer language models have received widespread public attention, yet their generated text is often surprising even to NLP researchers. In this survey, we discuss over 250 recent studies of English language model behavior before…

Computation and Language · Computer Science 2023-08-29 Tyler A. Chang , Benjamin K. Bergen

Fine-tuning large language models (LLMs) raises privacy concerns due to the risk of exposing sensitive training data. Federated learning (FL) mitigates this risk by keeping training samples on local devices, while facing the following…

Cryptography and Security · Computer Science 2025-05-15 Zhichao You , Xuewen Dong , Ke Cheng , Xutong Mu , Jiaxuan Fu , Shiyang Ma , Qiang Qu , Yulong Shen

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Cryptography and Security · Computer Science 2026-04-28 Zihan Liu , Yizhen Wang , Rui Wang , Xiu Tang , Sai Wu

One of the long-standing goals in optimisation and constraint programming is to describe a problem in natural language and automatically obtain an executable, efficient model. Large language models appear to bring this vision closer,…

Artificial Intelligence · Computer Science 2025-11-20 Alessio Pellegrino , Jacopo Mauro

Large Language Models are increasingly used in conversational systems such as digital personal assistants, shaping how people interact with technology through language. While their responses often sound fluent and natural, they can also…

Computation and Language · Computer Science 2025-12-24 Heet Bodara , Md Masum Mushfiq , Isma Farah Siddiqui

While task-agnostic debiasing provides notable generalizability and reduced reliance on downstream data, its impact on language modeling ability and the risk of relearning social biases from downstream task-specific data remain as the two…

Computation and Language · Computer Science 2024-06-07 Guangliang Liu , Milad Afshari , Xitong Zhang , Zhiyu Xue , Avrajit Ghosh , Bidhan Bashyal , Rongrong Wang , Kristen Johnson

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…

Social chatbots, also known as chit-chat chatbots, evolve rapidly with large pretrained language models. Despite the huge progress, privacy concerns have arisen recently: training data of large language models can be extracted via model…

Computation and Language · Computer Science 2022-05-23 Haoran Li , Yangqiu Song , Lixin Fan

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Cryptography and Security · Computer Science 2024-09-27 Federico Mazzone , Ahmad Al Badawi , Yuriy Polyakov , Maarten Everts , Florian Hahn , Andreas Peter

Although Large Language Models (LLMs) have demonstrated impressive capabilities across a wide range of tasks, growing concerns have emerged over the misuse of sensitive, copyrighted, or harmful data during training. To address these…

Cryptography and Security · Computer Science 2025-06-03 Jie Ren , Zhenwei Dai , Xianfeng Tang , Yue Xing , Shenglai Zeng , Hui Liu , Jingying Zeng , Qiankun Peng , Samarth Varshney , Suhang Wang , Qi He , Charu C. Aggarwal , Hui Liu

Vision-Language Models (VLMs) combine visual and textual understanding, rendering them well-suited for diverse tasks like generating image captions and answering visual questions across various domains. However, these capabilities are built…

Computer Vision and Pattern Recognition · Computer Science 2024-08-20 Simone Caldarella , Massimiliano Mancini , Elisa Ricci , Rahaf Aljundi

Multi-modal large language models (MLLMs) have made significant progress, yet their safety alignment remains limited. Typically, current open-source MLLMs rely on the alignment inherited from their language module to avoid harmful…

Cryptography and Security · Computer Science 2025-04-15 Yanbo Wang , Jiyang Guan , Jian Liang , Ran He

Large Language Models (LLMs) are gaining increasing attention due to their exceptional performance across numerous tasks. As a result, the general public utilize them as an influential tool for boosting their productivity while natural…

Cryptography and Security · Computer Science 2023-06-16 Zhigang Kan , Linbo Qiao , Hao Yu , Liwen Peng , Yifu Gao , Dongsheng Li

Large language models (LLMs) are rapidly being adopted for tasks like drafting emails, summarizing meetings, and answering health questions. In these settings, users may need to share private information (e.g., contact details, health…

Computation and Language · Computer Science 2026-01-16 Xiaoyuan Wu , Roshni Kaushik , Wenkai Li , Lujo Bauer , Koichi Onoue

Deep learning-based language models have achieved state-of-the-art results in a number of applications including sentiment analysis, topic labelling, intent classification and others. Obtaining text representations or embeddings using these…

Computation and Language · Computer Science 2021-08-30 Richard Plant , Dimitra Gkatzia , Valerio Giuffrida

Large Language Models (LLMs) trained on massive data capture rich information embedded in the training data. However, this also introduces the risk of privacy leakage, particularly involving personally identifiable information (PII).…

Computation and Language · Computer Science 2025-06-10 Wenshuo Dong , Qingsong Yang , Shu Yang , Lijie Hu , Meng Ding , Wanyu Lin , Tianhang Zheng , Di Wang

Machine learning models exhibit two seemingly contradictory phenomena: training data memorization, and various forms of forgetting. In memorization, models overfit specific training examples and become susceptible to privacy attacks. In…

The past a few years have witnessed the great success of large language models, demonstrating powerful capabilities in comprehending textual data and generating human-like languages. Large language models achieve success by being trained on…

Computation and Language · Computer Science 2025-03-20 Estrid He , Tabinda Sarwar , Ibrahim Khalil , Xun Yi , Ke Wang

As Speech Language Models (SLMs) transition from personal devices to shared, multi-user environments such as smart homes, a new challenge emerges: the model is expected to distinguish between users to manage information flow appropriately.…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-29 Yuxiang Wang , Hongyu Liu , Dekun Chen , Xueyao Zhang , Zhizheng Wu

Fine-tuning safety-aligned language models for downstream tasks often leads to substantial degradation of refusal behavior, making models vulnerable to adversarial misuse. While prior work has shown that safety-relevant features are encoded…

Machine Learning · Computer Science 2026-05-05 Sadia Asif , Mohammad Mohammadi Amiri