English
Related papers

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

200 papers

Large language models (LLMs) are increasingly deployed in high-stakes settings, yet they frequently violate contextual privacy by disclosing private information in situations where humans would exercise discretion. This raises a fundamental…

Computation and Language · Computer Science 2026-04-02 Haoran Wang , Li Xiong , Kai Shu

Data lakes enable the training of powerful machine learning models on sensitive, high-value medical datasets, but also introduce serious privacy risks due to potential leakage of protected health information. Recent studies show adversaries…

Machine Learning · Computer Science 2025-09-03 Elie Thellier , Huiyu Li , Nicholas Ayache , Hervé Delingette

We discover the emergence of \textit{basins} in the loss landscape of large language models. As model scale increases, LLMs become progressively more resilient to random perturbations in the parameter space, giving rise to expansive…

Machine Learning · Computer Science 2026-03-17 Huanran Chen , Yinpeng Dong , Zeming Wei , Yao Huang , Yichi Zhang , Hang Su , Jun Zhu

Large pre-trained language models (PLMs) have demonstrated strong performance on natural language understanding (NLU) tasks through fine-tuning. However, fine-tuned models still suffer from overconfident predictions, especially in…

Computation and Language · Computer Science 2023-05-31 Guande He , Jianfei Chen , Jun Zhu

With the advancement of language models (LMs), their exposure to private data is increasingly inevitable, and their deployment (especially for smaller ones) on personal devices, such as PCs and smartphones, has become a prevailing trend. In…

Computation and Language · Computer Science 2024-06-07 Kaiyan Zhang , Jianyu Wang , Ermo Hua , Biqing Qi , Ning Ding , Bowen Zhou

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Cryptography and Security · Computer Science 2025-09-09 Youjia Zheng , Mohammad Zandsalimy , Shanu Sushmita

Language models increasingly appear to learn similar representations, despite differences in training objectives, architectures, and data modalities. This emerging compatibility between independently trained models introduces new…

Artificial Intelligence · Computer Science 2026-05-26 Matt Gorbett , Suman Jana

Recent advancements in Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning with a few adversarially chosen…

Computation and Language · Computer Science 2025-03-03 Samuele Poppi , Zheng-Xin Yong , Yifei He , Bobbie Chern , Han Zhao , Aobo Yang , Jianfeng Chi

Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ability to often match the performance of full fine-tuning…

Machine Learning · Computer Science 2024-04-10 Aleksandar Petrov , Philip H. S. Torr , Adel Bibi

Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual stimuli and human judgments on visual cognition tasks,…

The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…

Cryptography and Security · Computer Science 2025-08-26 GodsGift Uzor , Hasan Al-Qudah , Ynes Ineza , Abdul Serwadda

Recent advances in natural language processing (NLP) have opened up greater opportunities to enable fine-tuned large language models (LLMs) to behave as more powerful interactive agents through improved instruction-following ability.…

Machine Learning · Computer Science 2025-10-27 Jerry Huang , Peng Lu , Qiuhao Zeng

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…

Computation and Language · Computer Science 2023-05-08 Davut Emre Tasar , Ceren Ocal Tasar

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

Computation and Language · Computer Science 2025-12-12 Lama Alssum , Hani Itani , Hasan Abed Al Kader Hammoud , Philip Torr , Adel Bibi , Bernard Ghanem

Self-disclosure, while being common and rewarding in social media interaction, also poses privacy risks. In this paper, we take the initiative to protect the user-side privacy associated with online self-disclosure through detection and…

Computation and Language · Computer Science 2024-06-25 Yao Dou , Isadora Krsek , Tarek Naous , Anubha Kabra , Sauvik Das , Alan Ritter , Wei Xu

As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognize and appropriately handle privacy-sensitive content is essential. We conduct a comprehensive evaluation of ten…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Laurens Samson , Nimrod Barazani , Sennay Ghebreab , Yuki M. Asano

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Artificial Intelligence · Computer Science 2026-02-26 Wenkai Li , Liwen Sun , Zhenxiang Guan , Xuhui Zhou , Maarten Sap

Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextual knowledge. These failures are often not wholesale reasoning collapses: in context-rich…

Computation and Language · Computer Science 2026-05-27 Hongbo Jin , Chi Wang , Haoran Tang , Zhongjing Du , Xu Jiang , Jingqi Tian , Qiaoman Zhang , Jiayu Ding

We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…

Artificial Intelligence · Computer Science 2026-02-10 Soumi Das , Camila Kolling , Mohammad Aflah Khan , Mahsa Amani , Bishwamittra Ghosh , Qinyuan Wu , Till Speicher , Krishna P. Gummadi

Conversational agents are increasingly woven into individuals' personal lives, yet users often underestimate the privacy risks associated with them. The moment users share information with these agents-such as large language models…

Cryptography and Security · Computer Science 2025-07-29 Ivoline Ngong , Swanand Kadhe , Hao Wang , Keerthiram Murugesan , Justin D. Weisz , Amit Dhurandhar , Karthikeyan Natesan Ramamurthy