English
Related papers

Related papers: Interpretable Privacy Preservation of Text Represe…

200 papers

Natural language reflects our private lives and identities, making its privacy concerns as broad as those of real life. Language models lack the ability to understand the context and sensitivity of text, and tend to memorize phrases present…

Machine Learning · Statistics 2022-02-15 Hannah Brown , Katherine Lee , Fatemehsadat Mireshghallah , Reza Shokri , Florian Tramèr

Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is…

Computation and Language · Computer Science 2024-11-06 Jiaxuan Wu , Zhengxian Wu , Yiming Xue , Juan Wen , Wanli Peng

Guaranteeing a certain level of user privacy in an arbitrary piece of text is a challenging issue. However, with this challenge comes the potential of unlocking access to vast data stores for training machine learning models and supporting…

Machine Learning · Computer Science 2019-10-22 Oluwaseyi Feyisetan , Tom Diethe , Thomas Drake

The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been identified as a central…

Computation and Language · Computer Science 2025-12-03 Yohan Mathew , Ollie Matthews , Robert McCarthy , Joan Velja , Christian Schroeder de Witt , Dylan Cope , Nandi Schoots

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

Computation and Language · Computer Science 2022-09-12 Jimit Majmudar , Christophe Dupuy , Charith Peris , Sami Smaili , Rahul Gupta , Richard Zemel

Recent steganographic schemes, starting with Meteor (CCS'21), rely on leveraging large language models (LLMs) to resolve a historically-challenging task of disguising covert communication as ``innocent-looking'' natural-language…

Cryptography and Security · Computer Science 2025-04-15 Neil Perry , Sanket Gupte , Nishant Pitta , Lior Rotem

Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based…

Computation and Language · Computer Science 2026-04-14 Ruiyi Yan , Yugo Murawaki

Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language…

Cryptography and Security · Computer Science 2026-01-22 Yuang Qi , Na Zhao , Qiyi Yao , Benlong Wu , Weiming Zhang , Nenghai Yu , Kejiang Chen

Large language models (LLMs) show early signs of artificial general intelligence but struggle with hallucinations. One promising solution to mitigate these hallucinations is to store external knowledge as embeddings, aiding LLMs in…

Computation and Language · Computer Science 2024-04-26 Zhihao Zhu , Ninglu Shao , Defu Lian , Chenwang Wu , Zheng Liu , Yi Yang , Enhong Chen

Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns…

Computation and Language · Computer Science 2025-08-22 Pritilata Saha , Abhirup Sinha

This article deals with adversarial attacks towards deep learning systems for Natural Language Processing (NLP), in the context of privacy protection. We study a specific type of attack: an attacker eavesdrops on the hidden representations…

Computation and Language · Computer Science 2018-08-29 Maximin Coavoux , Shashi Narayan , Shay B. Cohen

Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…

Computation and Language · Computer Science 2023-06-27 Minxue Xia , Hao Zhu

Linguistic steganography aims to conceal information within natural language text without being detected. An effective steganography approach should encode the secret message into a minimal number of language tokens while preserving the…

Information Theory · Computer Science 2025-02-05 Yu-Shin Huang , Chao Tian , Krishna Narayanan , Lizhong Zheng

Existing linguistic steganography methods primarily rely on content transformations to conceal secret messages. However, they often cause subtle yet looking-innocent deviations between normal and stego texts, posing potential security risks…

Cryptography and Security · Computer Science 2025-12-09 Lingyun Xiang , Chengfu Ou , Xu He , Zhongliang Yang , Yuling Liu

As is commonly known, the steganographic algorithms employ images, audio, video or text files as the medium to ensure hidden exchange of information between multiple contenders to protect the data from the prying eyes. However, using text…

Cryptography and Security · Computer Science 2012-03-19 Shraddha Dulera , Devesh Jinwala , Aroop Dasgupta

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of…

Computation and Language · Computer Science 2020-11-26 Sunipa Dev

Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users. In this paper, we propose a machine learning…

Machine Learning · Statistics 2019-06-06 Benjamin Baron , Mirco Musolesi

Large Visual Language Models (LVLMs) now pose a serious yet overlooked privacy threat, as they can infer a social media user's geolocation directly from shared images, leading to unintended privacy leakage. While adversarial image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Jiayi Zhu , Yihao Huang , Yue Cao , Xiaojun Jia , Qing Guo , Felix Juefei-Xu , Geguang Pu , Bin Wang

Differential Privacy (DP) for text has recently taken the form of text paraphrasing using language models and temperature sampling to better balance privacy and utility. However, the geometric distortion of DP regarding the structure and…

Computation and Language · Computer Science 2025-03-20 Stefan Arnold

Despite remarkable progress in steganography, embedding semantically rich, sentence-level information into carriers remains a challenging problem. In this work, we present a novel concept of Semantic Steganography, which aims to hide…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Huanqi Wu , Huangbiao Xu , Runfeng Xie , Jiaxin Cai , Kaixin Zhang , Xiao Ke