Related papers: Shielding Google's language toxicity model against…

Modifying characters of a piece of text to their visual similar ones often ap-pear in spam in order to fool inspection systems and other conditions, which we regard as a kind of adversarial attack to neural models. We pro-pose a way of…

Online social platforms are beset with hateful speech - content that expresses hatred for a person or group of people. Such content can frighten, intimidate, or silence platform users, and some of it can inspire other users to commit…

Detoxifying offensive language while preserving the speaker's original intent is a challenging yet critical goal for improving the quality of online interactions. Although large language models (LLMs) show promise in rewriting toxic…

Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulously altered inputs. Adversarial texts, however, are distinct…

Modern toxic speech detectors are incompetent in recognizing disguised offensive language, such as adversarial attacks that deliberately avoid known toxic lexicons, or manifestations of implicit bias. Building a large annotated dataset for…

Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based…

We introduce a new approach to tackle the problem of offensive language in online social media. Our approach uses unsupervised text style transfer to translate offensive sentences into non-offensive ones. We propose a new method for…

An adversarial example is an input transformed by small perturbations that machine learning models consistently misclassify. While there are a number of methods proposed to generate adversarial examples for text data, it is not trivial to…

The presence of toxic content has become a major problem for many online communities. Moderators try to limit this problem by implementing more and more refined comment filters, but toxic users are constantly finding new ways to circumvent…

Toxic online content has become a major issue in today's world due to an exponential increase in the use of internet by people of different cultures and educational background. Differentiating hate speech and offensive language is a key…

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…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Proprietary public APIs play a crucial and growing role as research tools among social scientists. Among such APIs, Google's machine learning-based Perspective API is extensively utilized for assessing the toxicity of social media messages,…

Language model detoxification aims to minimize the risk of generating offensive or harmful content in pretrained language models (PLMs) for safer deployment. Existing methods can be roughly categorized as finetuning-based and…

A rapidly increasing amount of human conversation occurs online. But divisiveness and conflict can fester in text-based interactions on social media platforms, in messaging apps, and on other digital forums. Such toxicity increases…

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…

Large language models (LLMs) excel in many diverse applications beyond language generation, e.g., translation, summarization, and sentiment analysis. One intriguing application is in text classification. This becomes pertinent in the realm…

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…

Open-domain neural dialogue models have achieved high performance in response ranking and evaluation tasks. These tasks are formulated as a binary classification of responses given in a dialogue context, and models generally learn to make…