相关论文: On The Robustness of Offensive Language Classifier…

Large language models (LLMs) have exhibited remarkable fluency across various tasks. However, their unethical applications, such as disseminating disinformation, have become a growing concern. Although recent works have proposed a number of…

With the increasing adoption of Large Language Models (LLMs), more customization is needed to ensure privacy-preserving and safe generation. We address this objective from two critical aspects: unlearning of sensitive information and…

With the growing use of social media and its availability, many instances of the use of offensive language have been observed across multiple languages and domains. This phenomenon has given rise to the growing need to detect the offensive…

The proliferation of social media platforms has led to an increase in the spread of hate speech, particularly targeting vulnerable communities. Unfortunately, existing methods for automatically identifying and blocking toxic language rely…

User generated text on social media often suffers from a lot of undesired characteristics including hatespeech, abusive language, insults etc. that are targeted to attack or abuse a specific group of people. Often such text is written…

Attacks on deep learning models are often difficult to identify and therefore are difficult to protect against. This problem is exacerbated by the use of public datasets that typically are not manually inspected before use. In this paper,…

Text classifiers are applied at scale in the form of one-size-fits-all solutions. Nevertheless, many studies show that classifiers are biased regarding different languages and dialects. When measuring and discovering these biases, some gaps…

Multimodal Large Language Models (MLLMs) have demonstrated exceptional performance in artificial intelligence by facilitating integrated understanding across diverse modalities, including text, images, video, audio, and speech. However,…

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…

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to…

A key challenge for automatic hate-speech detection on social media is the separation of hate speech from other instances of offensive language. Lexical detection methods tend to have low precision because they classify all messages…

Deep learning models achieve remarkable accuracy in computer vision tasks, yet remain vulnerable to adversarial examples--carefully crafted perturbations to input images that can deceive these models into making confident but incorrect…

Benchmarking outcomes increasingly govern trust, selection, and deployment of LLMs, yet these evaluations remain vulnerable to semantically equivalent adversarial perturbations. Prior work on adversarial robustness in NLP has emphasized…

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper…

Machine learning has been proven to be susceptible to carefully crafted samples, known as adversarial examples. The generation of these adversarial examples helps to make the models more robust and gives us an insight into the underlying…

This paper describes a novel study on using `Attention Mask' input in transformers and using this approach for detecting offensive content in both English and Persian languages. The paper's principal focus is to suggest a methodology to…

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…

Adversarial samples are strategically modified samples, which are crafted with the purpose of fooling a classifier at hand. An attacker introduces specially crafted adversarial samples to a deployed classifier, which are being…

Despite achieving impressive performance, state-of-the-art classifiers remain highly vulnerable to small, imperceptible, adversarial perturbations. This vulnerability has proven empirically to be very intricate to address. In this paper, we…

Offensive language detection is an ever-growing natural language processing (NLP) application. This growth is mainly because of the widespread usage of social networks, which becomes a mainstream channel for people to communicate, work, and…