English
Related papers

Related papers: Assessing Privacy Risks in Language Models: A Case…

200 papers

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

Cryptography and Security · Computer Science 2024-02-27 Nikhil Kandpal , Krishna Pillutla , Alina Oprea , Peter Kairouz , Christopher A. Choquette-Choo , Zheng Xu

Safety classifiers are essential safeguards within generative AI systems, filtering harmful content or identifying at-risk users when interacting with large language models. Despite their necessity, these models are trained on sensitive…

Machine Learning · Computer Science 2026-05-25 Anthony Hughes , Alexander Goldberg , Prince Jha , Adam Perer , Nikolaos Aletras , Niloofar Mireshghallah

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

Large Language Models (LLMs) pose significant privacy risks, potentially leaking training data due to implicit memorization. Existing privacy attacks primarily focus on membership inference attacks (MIAs) or data extraction attacks, but…

Computation and Language · Computer Science 2025-06-11 Wenlong Meng , Zhenyuan Guo , Lenan Wu , Chen Gong , Wenyan Liu , Weixian Li , Chengkun Wei , Wenzhi Chen

While being deployed in many critical applications as core components, machine learning (ML) models are vulnerable to various security and privacy attacks. One major privacy attack in this domain is membership inference, where an adversary…

Cryptography and Security · Computer Science 2020-09-11 Yang Zou , Zhikun Zhang , Michael Backes , Yang Zhang

The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…

Machine Learning · Computer Science 2022-03-24 Ganesh Del Grosso , Hamid Jalalzai , Georg Pichler , Catuscia Palamidessi , Pablo Piantanida

Large language models (LLMs) have significantly transformed the landscape of Natural Language Processing (NLP). Their impact extends across a diverse spectrum of tasks, revolutionizing how we approach language understanding and generations.…

Cryptography and Security · Computer Science 2025-06-13 Sara Abdali , Richard Anarfi , CJ Barberan , Jia He , Erfan Shayegani

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

Cryptography and Security · Computer Science 2024-09-04 Rui Wen , Zheng Li , Michael Backes , Yang Zhang

Large Language Models (LLMs) have become a cornerstone in the field of Natural Language Processing (NLP), offering transformative capabilities in understanding and generating human-like text. However, with their rising prominence, the…

Cryptography and Security · Computer Science 2024-03-26 Arijit Ghosh Chowdhury , Md Mofijul Islam , Vaibhav Kumar , Faysal Hossain Shezan , Vaibhav Kumar , Vinija Jain , Aman Chadha

Neural language models are known to have a high capacity for memorization of training samples. This may have serious privacy implications when training models on user content such as email correspondence. Differential privacy (DP), a…

Deep learning models often raise privacy concerns as they leak information about their training data. This enables an adversary to determine whether a data point was in a model's training set by conducting a membership inference attack…

Machine Learning · Computer Science 2020-06-11 Yigitcan Kaya , Sanghyun Hong , Tudor Dumitras

Membership inference attacks (MIAs) reveal whether specific data was used to train machine learning models, serving as important tools for privacy auditing and compliance assessment. Recent studies have reported that MIAs perform only…

Machine Learning · Computer Science 2025-09-09 Disha Makhija , Manoj Ghuhan Arivazhagan , Vinayshekhar Bannihatti Kumar , Rashmi Gangadharaiah

Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data…

Cryptography and Security · Computer Science 2025-11-24 Mona Khalil , Alberto Blanco-Justicia , Najeeb Jebreel , Josep Domingo-Ferrer

By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are…

Computation and Language · Computer Science 2024-10-02 Wei Huang , Yinggui Wang , Cen Chen

We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model,…

Cryptography and Security · Computer Science 2017-04-04 Reza Shokri , Marco Stronati , Congzheng Song , Vitaly Shmatikov

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

Summarization is a core task in Natural Language Processing (NLP). Recent advances in Large Language Models (LLMs) and the introduction of large context windows reaching millions of tokens make it possible to process entire books in a…

Computation and Language · Computer Science 2026-03-12 Tairan Fu , Javier Conde , Pedro Reviriego , Javier Coronado-Blázquez , Nina Melero , Elena Merino-Gómez

Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scenarios. For example,…

Machine Learning · Computer Science 2022-04-27 Guoyao Li , Shahbaz Rezaei , Xin Liu

In several jurisdictions, the regulatory framework on the release and sharing of personal data is being extended to machine learning (ML). The implicit assumption is that disclosing a trained ML model entails a privacy risk for any personal…

Cryptography and Security · Computer Science 2025-11-14 Josep Domingo-Ferrer

Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making. However, these advancements have also come with significant privacy concerns. While significant…

Cryptography and Security · Computer Science 2026-01-27 Yuntao Du , Zitao Li , Ninghui Li , Bolin Ding