English
Related papers

Related papers: Text Analysis in Adversarial Settings: Does Decept…

200 papers

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Oscar Chew , Po-Yi Lu , Jayden Lin , Hsuan-Tien Lin

Intuitively, human readers cope easily with errors in text; typos, misspelling, word substitutions, etc. do not unduly disrupt natural reading. Previous work indicates that letter transpositions result in increased reading times, but it is…

Computation and Language · Computer Science 2019-05-21 Michael Hahn , Frank Keller , Yonatan Bisk , Yonatan Belinkov

Debiasing methods that seek to mitigate the tendency of Language Models (LMs) to occasionally output toxic or inappropriate text have recently gained traction. In this paper, we propose a standardized protocol which distinguishes methods…

Computation and Language · Computer Science 2023-05-24 Robert Morabito , Jad Kabbara , Ali Emami

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…

Computation and Language · Computer Science 2016-08-08 Mohammad Taher Pilehvar , Nigel Collier

The advent of instruction-tuned language models that convincingly mimic human writing poses a significant risk of abuse. However, such abuse may be counteracted with the ability to detect whether a piece of text was composed by a language…

Computation and Language · Computer Science 2024-05-09 Rafael Rivera Soto , Kailin Koch , Aleem Khan , Barry Chen , Marcus Bishop , Nicholas Andrews

Biased associations have been a challenge in the development of classifiers for detecting toxic language, hindering both fairness and accuracy. As potential solutions, we investigate recently introduced debiasing methods for text…

Computation and Language · Computer Science 2021-02-02 Xuhui Zhou , Maarten Sap , Swabha Swayamdipta , Noah A. Smith , Yejin Choi

This paper focuses on text detoxification, i.e., automatically converting toxic text into non-toxic text. This task contributes to safer and more respectful online communication and can be considered a Text Style Transfer (TST) task, where…

Computation and Language · Computer Science 2024-06-11 Sourabrata Mukherjee , Akanksha Bansal , Atul Kr. Ojha , John P. McCrae , Ondřej Dušek

This study analyzes the relationship between non-verbal information (e.g., genres) and text design (e.g., font style, character color, etc.) through the classification of book genres using text design on book covers. Text images have both…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Daichi Haraguchi , Brian Kenji Iwana , Seiichi Uchida

With social media growth, users employ stylistic fonts and font-like emoji to express individuality, creating visually appealing text that remains human-readable. However, these fonts introduce hidden vulnerabilities in NLP models: while…

Computation and Language · Computer Science 2025-10-23 Yangshijie Zhang , Xinda Wang , Jialin Liu , Wenqiang Wang , Zhicong Ma , Xingxing Jia

This paper shows that standard assessment methodology for style transfer has several significant problems. First, the standard metrics for style accuracy and semantics preservation vary significantly on different re-runs. Therefore one has…

Computation and Language · Computer Science 2022-11-15 Alexey Tikhonov , Viacheslav Shibaev , Aleksander Nagaev , Aigul Nugmanova , Ivan P. Yamshchikov

Differential Privacy (DP) for text matured from disjointed word-level substitutions to contiguous sentence-level rewriting by leveraging the generative capacity of language models. While this form of text privatization is best suited for…

Computation and Language · Computer Science 2026-04-30 Stefan Arnold

We introduce a data-centric hypothesis-testing framework to quantify the influence of sequentially correlated literary properties--such as thematic continuity--on textual classification tasks. Our method models label sequences as stochastic…

Computation and Language · Computer Science 2025-04-25 Gideon Yoffe , Nachum Dershowitz , Ariel Vishne , Barak Sober

Documents as short as a single sentence may inadvertently reveal sensitive information about their authors, including e.g. their gender or ethnicity. Style transfer is an effective way of transforming texts in order to remove any…

Computation and Language · Computer Science 2021-09-21 David Ifeoluwa Adelani , Miaoran Zhang , Xiaoyu Shen , Ali Davody , Thomas Kleinbauer , Dietrich Klakow

In this paper, we investigate the efficacy of large language models (LLMs) in obfuscating authorship by paraphrasing and altering writing styles. Rather than adopting a holistic approach that evaluates performance across the entire dataset,…

Computation and Language · Computer Science 2025-05-20 Mohammad Shokri , Sarah Ita Levitan , Rivka Levitan

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

Computation and Language · Computer Science 2020-05-28 Zhifeng Hu , Serhii Havrylov , Ivan Titov , Shay B. Cohen

Nowadays, deep learning has been widely used. In natural language learning, the analysis of complex semantics has been achieved because of its high degree of flexibility. The deceptive opinions detection is an important application area in…

Computation and Language · Computer Science 2018-03-20 Siyuan Zhao , Zhiwei Xu , Limin Liu , Mengjie Guo

An increasingly common socio-technical problem is people being taken in by offers that sound ``too good to be true'', where persuasion and trust shape decision-making. This paper investigates how \abr{ai} can help detect these deceptive…

Computation and Language · Computer Science 2025-06-06 Wichayaporn Wongkamjan , Yanze Wang , Feng Gu , Denis Peskoff , Jonathan K. Kummerfeld , Jonathan May , Jordan Lee Boyd-Graber

Social media features substantial stylistic variation, raising new challenges for syntactic analysis of online writing. However, this variation is often aligned with author attributes such as age, gender, and geography, as well as more…

Computation and Language · Computer Science 2018-04-23 Murali Raghu Babu Balusu , Taha Merghani , Jacob Eisenstein

Current text classification approaches usually focus on the content to be classified. Contextual aspects (both linguistic and extra-linguistic) are usually neglected, even in tasks based on online discussions. Still in many cases the…

Computation and Language · Computer Science 2026-03-30 Nicolò Penzo , Antonio Longa , Bruno Lepri , Sara Tonelli , Marco Guerini

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn