English
Related papers

Related papers: IncogniText: Privacy-enhancing Conditional Text An…

200 papers

LLMs have been found to memorize training textual sequences and regurgitate verbatim said sequences during text generation time. This fact is known to be the cause of privacy and related (e.g., copyright) problems. Unlearning in LLMs then…

Machine Learning · Computer Science 2024-05-07 George-Octavian Barbulescu , Peter Triantafillou

In the context of information systems, text sanitization techniques are used to identify and remove sensitive data to comply with security and regulatory requirements. Even though many methods for privacy preservation have been proposed,…

Computation and Language · Computer Science 2023-11-21 Federico Albanese , Daniel Ciolek , Nicolas D'Ippolito

Crowdsourced data used in machine learning services might carry sensitive information about attributes that users do not want to share. Various methods have been proposed to minimize the potential information leakage of sensitive attributes…

Machine Learning · Computer Science 2020-10-27 Han Zhao , Jianfeng Chi , Yuan Tian , Geoffrey J. Gordon

The goal of voice anonymization is to modify an audio such that the true identity of its speaker is hidden. Research on this task is typically limited to the same English read speech datasets, thus the efficacy of current methods for other…

Audio and Speech Processing · Electrical Eng. & Systems 2025-07-03 Sarina Meyer , Ekaterina Kolos , Ngoc Thang Vu

The development of artificial intelligence has significantly transformed people's lives. However, it has also posed a significant threat to privacy and security, with numerous instances of personal information being exposed online and…

Cryptography and Security · Computer Science 2024-02-28 Le Yang , Miao Tian , Duan Xin , Qishuo Cheng , Jiajian Zheng

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Cryptography and Security · Computer Science 2024-02-13 Raha Moraffah , Shubh Khandelwal , Amrita Bhattacharjee , Huan Liu

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Computation and Language · Computer Science 2025-03-26 Kenneth Alperin , Rohan Leekha , Adaku Uchendu , Trang Nguyen , Srilakshmi Medarametla , Carlos Levya Capote , Seth Aycock , Charlie Dagli

In speech technologies, speaker's voice representation is used in many applications such as speech recognition, voice conversion, speech synthesis and, obviously, user authentication. Modern vocal representations of the speaker are based on…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Paul-Gauthier Noé , Mohammad Mohammadamini , Driss Matrouf , Titouan Parcollet , Andreas Nautsch , Jean-François Bonastre

Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation,…

Cryptography and Security · Computer Science 2020-04-15 Jinyuan Jia , Neil Zhenqiang Gong

Large Language Models (LLMs) such as ChatGPT can infer personal attributes from seemingly innocuous text, raising privacy risks beyond memorized data leakage. While prior work has demonstrated these risks, little is known about how users…

Human-Computer Interaction · Computer Science 2025-09-16 Synthia Wang , Sai Teja Peddinti , Nina Taft , Nick Feamster

Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. Anonymization…

Machine Learning · Computer Science 2025-11-03 Héber H. Arcolezi , Mina Alishahi , Adda-Akram Bendoukha , Nesrine Kaaniche

While audio recordings in real life provide insights into social dynamics and conversational behavior, they also raise concerns about the privacy of personal, sensitive data. This article explores the effectiveness of restricting recordings…

Audio and Speech Processing · Electrical Eng. & Systems 2026-02-04 Jule Pohlhausen , Jörg Bitzer

In 2011 Bhaskar et al. pointed out that in many cases one can ensure sufficient level of privacy without adding noise by utilizing adversarial uncertainty. Informally speaking, this observation comes from the fact that if at least a part of…

Cryptography and Security · Computer Science 2020-09-23 Krzysztof Grining , Marek Klonowski

The rapid advancement of customized Large Language Models (LLMs) offers considerable convenience. However, it also intensifies concerns regarding the protection of copyright/confidential information. With the extensive adoption of private…

Cryptography and Security · Computer Science 2024-12-18 Yuehan Zhang , Peizhuo Lv , Yinpeng Liu , Yongqiang Ma , Wei Lu , Xiaofeng Wang , Xiaozhong Liu , Jiawei Liu

With the popularity of large language models (LLMs), undesirable societal problems like misinformation production and academic misconduct have been more severe, making LLM-generated text detection now of unprecedented importance. Although…

Computation and Language · Computer Science 2025-06-19 Yuhui Shi , Yehan Yang , Qiang Sheng , Hao Mi , Beizhe Hu , Chaoxi Xu , Juan Cao

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

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

Cryptography and Security · Computer Science 2025-02-11 Michele Miranda , Elena Sofia Ruzzetti , Andrea Santilli , Fabio Massimo Zanzotto , Sébastien Bratières , Emanuele Rodolà

Authorship obfuscation, rewriting a text to intentionally obscure the identity of the author, is an important but challenging task. Current methods using large language models (LLMs) lack interpretability and controllability, often ignoring…

Computation and Language · Computer Science 2024-08-29 Jillian Fisher , Skyler Hallinan , Ximing Lu , Mitchell Gordon , Zaid Harchaoui , Yejin Choi

The steadily increasing utilization of data-driven methods and approaches in areas that handle sensitive personal information such as in law enforcement mandates an ever increasing effort in these institutions to comply with data protection…

Artificial Intelligence · Computer Science 2025-01-14 Manuel Eberhardinger , Patrick Takenaka , Daniel Grießhaber , Johannes Maucher

How can we learn a representation with high predictive power while preserving user privacy? We present an adversarial representation learning method for sanitizing sensitive content from the learned representation. Specifically, we…

Machine Learning · Computer Science 2025-07-15 Tassilo Klein , Moin Nabi