English
Related papers

Related papers: Towards Building a Robust Toxicity Predictor

200 papers

The language models, especially the basic text classification models, have been shown to be susceptible to textual adversarial attacks such as synonym substitution and word insertion attacks. To defend against such attacks, a growing body…

Cryptography and Security · Computer Science 2024-06-12 Xinyu Zhang , Hanbin Hong , Yuan Hong , Peng Huang , Binghui Wang , Zhongjie Ba , Kui Ren

The rise of cyberbullying in social media platforms involving toxic comments has escalated the need for effective ways to monitor and moderate online interactions. Existing solutions of automated toxicity detection systems, are based on a…

Artificial Intelligence · Computer Science 2026-02-11 Michail S. Alexiou , J. Sukarno Mertoguno

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

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models (VLMs). This part of the training pipeline is critical for supplying…

Cryptography and Security · Computer Science 2025-06-30 Stanley Wu , Ronik Bhaskar , Anna Yoo Jeong Ha , Shawn Shan , Haitao Zheng , Ben Y. Zhao

With the great success of deep neural networks, adversarial learning has received widespread attention in various studies, ranging from multi-class learning to multi-label learning. However, existing adversarial attacks toward multi-label…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Yuchen Sun , Qianqian Xu , Zitai Wang , Qingming Huang

Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are correctly labeled.…

Machine Learning · Computer Science 2023-10-31 Wencong You , Zayd Hammoudeh , Daniel Lowd

The widespread use of large language models (LLMs) is increasing the demand for methods that detect machine-generated text to prevent misuse. The goal of our study is to stress test the detectors' robustness to malicious attacks under…

Computation and Language · Computer Science 2024-02-20 Yichen Wang , Shangbin Feng , Abe Bohan Hou , Xiao Pu , Chao Shen , Xiaoming Liu , Yulia Tsvetkov , Tianxing He

We propose an efficient method to generate white-box adversarial examples to trick a character-level neural classifier. We find that only a few manipulations are needed to greatly decrease the accuracy. Our method relies on an atomic flip…

Computation and Language · Computer Science 2018-05-25 Javid Ebrahimi , Anyi Rao , Daniel Lowd , Dejing Dou

Recent studies show that models trained by continual learning can achieve the comparable performances as the standard supervised learning and the learning flexibility of continual learning models enables their wide applications in the real…

Machine Learning · Computer Science 2023-04-03 Tao Bai , Chen Chen , Lingjuan Lyu , Jun Zhao , Bihan Wen

Large pre-trained Vision-Language Models (VLMs) like CLIP, despite having remarkable generalization ability, are highly vulnerable to adversarial examples. This work studies the adversarial robustness of VLMs from the novel perspective of…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Lin Li , Haoyan Guan , Jianing Qiu , Michael Spratling

The robustness of Text-to-SQL parsers against adversarial perturbations plays a crucial role in delivering highly reliable applications. Previous studies along this line primarily focused on perturbations in the natural language question…

Computation and Language · Computer Science 2022-12-21 Xinyu Pi , Bing Wang , Yan Gao , Jiaqi Guo , Zhoujun Li , Jian-Guang Lou

Deep neural networks usually require large labeled datasets for training to achieve state-of-the-art performance in many tasks, such as image classification and natural language processing. Although a lot of data is created each day by…

Machine Learning · Computer Science 2021-09-03 Jing Lin , Ryan Luley , Kaiqi Xiong

Black-box textual adversarial attacks are challenging due to the lack of model information and the discrete, non-differentiable nature of text. Existing methods often lack versatility for attacking different models, suffer from limited…

Computation and Language · Computer Science 2025-01-22 Mingze Ni , Yongshun Gong , Wei Liu

This paper introduces a novel adversarial attack method targeting text classification models, termed the Modified Word Saliency-based Adversarial At-tack (MWSAA). The technique builds upon the concept of word saliency to strategically…

Computation and Language · Computer Science 2025-05-13 Hetvi Waghela , Sneha Rakshit , Jaydip Sen

The detrimental effects of toxicity in competitive online video games are widely acknowledged, prompting publishers to monitor player chat conversations. This is challenging due to the context-dependent nature of toxicity, often spread…

Computation and Language · Computer Science 2025-04-03 Adrien Schurger-Foy , Rafal Dariusz Kocielnik , Caglar Gulcehre , R. Michael Alvarez

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Cryptography and Security · Computer Science 2023-10-23 Xilie Xu , Keyi Kong , Ning Liu , Lizhen Cui , Di Wang , Jingfeng Zhang , Mohan Kankanhalli

We introduce a novel class of adversarial attacks on toxicity detection models that exploit language models' failure to interpret spatially structured text in the form of ASCII art. To evaluate the effectiveness of these attacks, we propose…

Computation and Language · Computer Science 2025-09-25 Sergey Berezin , Reza Farahbakhsh , Noel Crespi

Algorithmic bias often arises as a result of differential subgroup validity, in which predictive relationships vary across groups. For example, in toxic language detection, comments targeting different demographic groups can vary markedly…

Machine Learning · Computer Science 2023-03-08 Soumyajit Gupta , Sooyong Lee , Maria De-Arteaga , Matthew Lease

Clean-label (CL) attack is a form of data poisoning attack where an adversary modifies only the textual input of the training data, without requiring access to the labeling function. CL attacks are relatively unexplored in NLP, as compared…

Computation and Language · Computer Science 2023-06-01 Ashim Gupta , Amrith Krishna

In different NLP tasks, detecting harmful content is crucial for online environments, especially with the growing influence of social media. However, previous research has two main issues: 1) a lack of data in low-resource settings, and 2)…

Computation and Language · Computer Science 2025-04-16 Zheng Hui , Zhaoxiao Guo , Hang Zhao , Juanyong Duan , Congrui Huang