English
Related papers

Related papers: Training Data Leakage Analysis in Language Models

200 papers

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

Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage…

Artificial Intelligence · Computer Science 2021-01-14 Guangneng Hu , Qiang Yang

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

Artificial Intelligence · Computer Science 2024-12-09 Georgios Feretzakis , Vassilios S. Verykios

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Cryptography and Security · Computer Science 2024-07-16 Yixin Liu , Hongsheng Hu , Xun Chen , Xuyun Zhang , Lichao Sun

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

Cryptography and Security · Computer Science 2020-12-10 Liwei Song , Prateek Mittal

With the growing emphasis on users' privacy, federated learning has become more and more popular. Many architectures have been raised for a better security. Most architecture work on the assumption that data's gradient could not leak…

Cryptography and Security · Computer Science 2020-03-12 Zhaorui Li , Zhicong Huang , Chaochao Chen , Cheng Hong

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

Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…

Computation and Language · Computer Science 2022-06-27 Xuandong Zhao , Lei Li , Yu-Xiang Wang

Large Language Models for Code (LLMs4Code) have achieved strong performance in code generation, but recent studies reveal that they may memorize and leak sensitive information contained in training data, posing serious privacy risks. To…

Cryptography and Security · Computer Science 2026-01-29 Shanzhi Gu , Zhaoyang Qu , Ruotong Geng , Mingyang Geng , Shangwen Wang , Chuanfu Xu , Haotian Wang , Zhipeng Lin , Dezun Dong

Large Language Models (LLMs) have become integral to various software engineering tasks, including code generation, bug detection, and repair. To evaluate model performance in these domains, numerous bug benchmarks containing real-world…

Software Engineering · Computer Science 2025-04-01 Daniel Ramos , Claudia Mamede , Kush Jain , Paulo Canelas , Catarina Gamboa , Claire Le Goues

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with…

Computation and Language · Computer Science 2022-07-19 Weiyan Shi , Aiqi Cui , Evan Li , Ruoxi Jia , Zhou Yu

Thanks to the explosive growth of data and the development of computational resources, it is possible to build pre-trained models that can achieve outstanding performance on various tasks, such as neural language processing, computer…

Artificial Intelligence · Computer Science 2024-11-13 Meng Yang , Tianqing Zhu , Chi Liu , WanLei Zhou , Shui Yu , Philip S. Yu

Modern mix networks improve over Tor and provide stronger privacy guarantees by robustly obfuscating metadata. As long as a message is routed through at least one honest mixnode, the privacy of the users involved is safeguarded. However,…

Cryptography and Security · Computer Science 2025-06-11 Vasilios Mavroudis , Tariq Elahi

Large language models have gained significant popularity because of their ability to generate human-like text and potential applications in various fields, such as Software Engineering. Large language models for code are commonly trained on…

Cryptography and Security · Computer Science 2024-01-17 Ali Al-Kaswan , Maliheh Izadi , Arie van Deursen

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

Neural networks pose a privacy risk to training data due to their propensity to memorise and leak information. Focusing on image classification, we show that neural networks also unintentionally memorise unique features even when they occur…

Machine Learning · Computer Science 2022-06-06 John Hartley , Sotirios A. Tsaftaris

Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…

Cryptography and Security · Computer Science 2021-12-10 Dominik Wunderlich , Daniel Bernau , Francesco Aldà , Javier Parra-Arnau , Thorsten Strufe

Machine learning models have been shown to leak information violating the privacy of their training set. We focus on membership inference attacks on machine learning models which aim to determine whether a data point was used to train the…

Cryptography and Security · Computer Science 2020-09-02 Shadi Rahimian , Tribhuvanesh Orekondy , Mario Fritz

Large language models (LLMs) have achieved remarkable performance on a wide range of tasks. However, recent studies have shown that LLMs can memorize training data and simple repeated tokens can trick the model to leak the data. In this…

Cryptography and Security · Computer Science 2024-05-21 Yang Bai , Ge Pei , Jindong Gu , Yong Yang , Xingjun Ma

When building machine learning models using sensitive data, organizations should ensure that the data processed in such systems is adequately protected. For projects involving machine learning on personal data, Article 35 of the GDPR…

Cryptography and Security · Computer Science 2020-07-21 Sasi Kumar Murakonda , Reza Shokri
‹ Prev 1 4 5 6 7 8 10 Next ›