相关论文: White-Box Attacks on Hate-speech BERT Classifiers …

Generating high-quality textual adversarial examples is critical for investigating the pitfalls of natural language processing (NLP) models and further promoting their robustness. Existing attacks are usually realized through word-level or…

Word-level adversarial attacks have shown success in NLP models, drastically decreasing the performance of transformer-based models in recent years. As a countermeasure, adversarial defense has been explored, but relatively few efforts have…

Adversarial attacks optimize against models to defeat defenses. Existing defenses are static, and stay the same once trained, even while attacks change. We argue that models should fight back, and optimize their defenses against attacks at…

Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach…

The context-dependent nature of online aggression makes annotating large collections of data extremely difficult. Previously studied datasets in abusive language detection have been insufficient in size to efficiently train deep learning…

Despite the extensive communication benefits offered by social media platforms, numerous challenges must be addressed to ensure user safety. One of the most significant risks faced by users on these platforms is targeted hate speech. Social…

The design of better automated dialogue evaluation metrics offers the potential of accelerate evaluation research on conversational AI. However, existing trainable dialogue evaluation models are generally restricted to classifiers trained…

Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak…

In the digital age of today, the internet has become an indispensable platform for people's lives, work, and information exchange. However, the problem of violent text proliferation in the network environment has arisen, which has brought…

In today's digital world, cyberbullying is a serious problem that can harm the mental and physical health of people who use social media. This paper explains just how serious cyberbullying is and how it really affects indi-viduals exposed…

Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substitutions). While…

Deep learning has undoubtedly offered tremendous improvements in the performance of state-of-the-art speech emotion recognition (SER) systems. However, recent research on adversarial examples poses enormous challenges on the robustness of…

Although deep neural networks have shown promising performances on various tasks, even achieving human-level performance on some, they are shown to be susceptible to incorrect predictions even with imperceptibly small perturbations to an…

In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model information: the underlying architecture and primary training…

Large language models play a crucial role in modern natural language processing technologies. However, their extensive use also introduces potential security risks, such as the possibility of black-box attacks. These attacks can embed…

Hate speech is increasingly prevalent online, and its negative outcomes include increased prejudice, extremism, and even offline hate crime. Automatic detection of online hate speech can help us to better understand these impacts. However,…

The widespread use of social media necessitates reliable and efficient detection of offensive content to mitigate harmful effects. Although sophisticated models perform well on individual datasets, they often fail to generalize due to…

We investigate MT evaluation metric performance on adversarially-synthesized texts, to shed light on metric robustness. We experiment with word- and character-level attacks on three popular machine translation metrics: BERTScore, BLEURT,…

The capabilities and limitations of BERT and similar models are still unclear when it comes to learning syntactic abstractions, in particular across languages. In this paper, we use the task of subordinate-clause detection within and across…

The widespread use of text-based communication on social media-through chats, comments, and microblogs-has improved user interaction but has also led to an increase in offensive content, including hate speech, racism, and other forms of…