English
Related papers

Related papers: PATCH: Mitigating PII Leakage in Language Models w…

200 papers

Federated learning (FL) enables collaborative training across organizational silos without sharing raw data, making it attractive for privacy-sensitive applications. With the rapid adoption of large language models (LLMs), federated…

Cryptography and Security · Computer Science 2026-04-17 Mohamed Shaaban , Mohamed Elmahallawy

Large language models (LLMs) are commonly adapted to downstream tasks through fine-tuning, but fine-tuning data often contains sensitive information that may be leaked by the resulting model. Differential privacy (DP) offers formal…

Machine Learning · Computer Science 2026-05-19 Haichao Sha , Zihao Wang , Yuncheng Wu , Hong Chen , Wei Dong

Latent Dirichlet Allocation (LDA) is a popular topic modeling technique for discovery of hidden semantic architecture of text datasets, and plays a fundamental role in many machine learning applications. However, like many other machine…

Machine Learning · Computer Science 2019-07-02 Fangyuan Zhao , Xuebin Ren , Shusen Yang , Xinyu Yang

Current techniques for privacy auditing of large language models (LLMs) have limited efficacy -- they rely on basic approaches to generate canaries which leads to weak membership inference attacks that in turn give loose lower bounds on the…

Cryptography and Security · Computer Science 2025-03-11 Ashwinee Panda , Xinyu Tang , Milad Nasr , Christopher A. Choquette-Choo , Prateek Mittal

Federated Learning (FL) allows for the training of Machine Learning models in a collaborative manner without the need to share sensitive data. However, it remains vulnerable to Gradient Leakage Attacks (GLAs), which can reveal private…

Machine Learning · Computer Science 2025-10-29 Miguel Fernandez-de-Retana , Unai Zulaika , Rubén Sánchez-Corcuera , Aitor Almeida

Privacy preservation has served as a key metric in designing Nash equilibrium (NE) computation algorithms. Although differential privacy (DP) has been widely employed for privacy guarantees, it does not exploit prior distributional…

Computer Science and Game Theory · Computer Science 2025-10-27 Zhaoyang Cheng , Guanpu Chen , Tobias J. Oechtering , Mikael Skoglund

Recent Deep Learning (DL) advancements in solving complex real-world tasks have led to its widespread adoption in practical applications. However, this opportunity comes with significant underlying risks, as many of these models rely on…

Cryptography and Security · Computer Science 2024-02-20 Shubhi Shukla , Manaar Alam , Sarani Bhattacharya , Debdeep Mukhopadhyay , Pabitra Mitra

The responses generated by Large Language Models (LLMs) can include sensitive information from individuals and organizations, leading to potential privacy leakage. This work implements Influence Functions (IFs) to trace privacy leakage back…

Machine Learning · Computer Science 2024-09-06 Jinxin Liu , Zao Yang

This paper studies leakage of user passwords and PINs based on observations of typing feedback on screens or from projectors in the form of masked characters that indicate keystrokes. To this end, we developed an attack called Password and…

Past work has shown that large language models are susceptible to privacy attacks, where adversaries generate sequences from a trained model and detect which sequences are memorized from the training set. In this work, we show that the…

Cryptography and Security · Computer Science 2022-12-21 Nikhil Kandpal , Eric Wallace , Colin Raffel

The interactive use of large language models (LLMs) in AI assistants (at work, home, etc.) introduces a new set of inference-time privacy risks: LLMs are fed different types of information from multiple sources in their inputs and are…

Artificial Intelligence · Computer Science 2024-07-02 Niloofar Mireshghallah , Hyunwoo Kim , Xuhui Zhou , Yulia Tsvetkov , Maarten Sap , Reza Shokri , Yejin Choi

As large language models (LLMs) become integral to multi-agent systems, new privacy risks emerge that extend beyond memorization, direct inference, or single-turn evaluations. In particular, seemingly innocuous responses, when composed…

Cryptography and Security · Computer Science 2025-09-19 Vaidehi Patil , Elias Stengel-Eskin , Mohit Bansal

Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidden from users, and sensitive data passes through shared contexts. We test whether models…

Cryptography and Security · Computer Science 2026-05-12 Ari Holtzman , Peter West

There are many approaches in mobile data ecosystem that inspect network traffic generated by applications running on user's device to detect personal data exfiltration from the user's device. State-of-the-art methods rely on features…

Machine Learning · Computer Science 2025-02-14 Rishika Kohli , Shaifu Gupta , Manoj Singh Gaur

AI chatbots have quietly become the world's most popular therapists, coaches, and confidants. Users of cloud-based LLM services are increasingly shifting from simple queries like idea generation and poem writing, to deeply personal…

Human-Computer Interaction · Computer Science 2026-04-08 Max Holschneider , Saetbyeol LeeYouk

The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally…

Cryptography and Security · Computer Science 2026-04-21 Aman Panjwani

The collection and availability of big data, combined with advances in pre-trained models (e.g. BERT), have revolutionized the predictive performance of natural language processing tasks. This allows corporations to provide machine learning…

Cryptography and Security · Computer Science 2022-11-01 Xuanli He , Chen Chen , Lingjuan Lyu , Qiongkai Xu

The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…

Cryptography and Security · Computer Science 2025-10-03 Niloofar Mireshghallah , Tianshi Li

Differential privacy (DP) is the de facto privacy standard against privacy leakage attacks, including many recently discovered ones against large language models (LLMs). However, we discovered that LLMs could reconstruct the altered/removed…

Cryptography and Security · Computer Science 2025-09-19 Shuchao Pang , Zhigang Lu , Haichen Wang , Peng Fu , Yongbin Zhou , Minhui Xue

As the capabilities of pre-trained large language models (LLMs) continue to advance, the "pre-train and fine-tune" paradigm has become increasingly mainstream, leading to the development of various fine-tuning methods. However, the privacy…

Computation and Language · Computer Science 2025-07-02 Jie Hou , Chuxiong Wu , Lannan Luo , Qiang Zeng