相关论文: VertAttack: Taking advantage of Text Classifiers' …

In virtual assistant (VA) systems it is important to reject or redirect user queries that fall outside the scope of the system. One of the most accurate approaches for out-of-scope (OOS) rejection is to combine it with the task of intent…

Transfer adversarial attack is a non-trivial black-box adversarial attack that aims to craft adversarial perturbations on the surrogate model and then apply such perturbations to the victim model. However, the transferability of…

Natural language processing models based on neural networks are vulnerable to adversarial examples. These adversarial examples are imperceptible to human readers but can mislead models to make the wrong predictions. In a black-box setting,…

Innovations in annotation methodology have been a catalyst for Reading Comprehension (RC) datasets and models. One recent trend to challenge current RC models is to involve a model in the annotation process: humans create questions…

RNN-Transducers (RNN-Ts) have gained widespread acceptance as an end-to-end model for speech to text conversion because of their high accuracy and streaming capabilities. A typical RNN-T independently encodes the input audio and the text…

Text classification algorithms investigate the intricate relationships between words or phrases and attempt to deduce the document's interpretation. In the last few years, these algorithms have progressed tremendously. Transformer…

The widespread adoption of ChatGPT has raised concerns about its misuse, highlighting the need for robust detection of AI-generated text. Current word-level detectors are vulnerable to paraphrasing or simple prompts (PSP), suffer from…

In recent years, the introduction of the Transformer models sparked a revolution in natural language processing (NLP). BERT was one of the first text encoders using only the attention mechanism without any recurrent parts to achieve…

Prior studies have shown that distinguishing text generated by Large Language Models (LLMs) from human-written one is highly challenging for humans, and often no better than random guessing. To verify the generalizability of this finding…

Recent advances in large language models (LLMs) and the intensifying popularity of ChatGPT-like applications have blurred the boundary of high-quality text generation between humans and machines. However, in addition to the anticipated…

Large language models (LLMs) have shown the capability to generate fluent and logical content, presenting significant challenges to machine-generated text detection, particularly text polished by adversarial perturbations such as…

Existing hard-label text attacks often rely on inefficient "outside-in" strategies that traverse vast search spaces. We propose PivotAttack, a query-efficient "inside-out" framework. It employs a Multi-Armed Bandit algorithm to identify…

Motivated by the success of powerful while expensive techniques to recognize words in a holistic way, object proposals techniques emerge as an alternative to the traditional text detectors. In this paper we introduce a novel object…

Patch attacks, one of the most threatening forms of physical attack in adversarial examples, can lead networks to induce misclassification by modifying pixels arbitrarily in a continuous region. Certifiable patch defense can guarantee…

This study uses the cosine similarity ratio, embedding regression, and manual re-annotation to diagnose hate speech classification. We begin by computing cosine similarity ratio on a dataset "Measuring Hate Speech" that contains 135,556…

As LLMs rapidly advance, increasing concerns arise regarding risks about actual authorship of texts we see online and in real world. The task of distinguishing LLM-authored texts is complicated by the nuanced and overlapping behaviors of…

Although researchers' attention is more focused on the performance of Transformer models, the interpretation of Transformer can never be ignored. Gradient is widely utilized in Transformer interpretation. From the perspective of attention…

Hate speech is a widespread and harmful form of online discourse, encompassing slurs and defamatory posts that can have serious social, psychological, and sometimes physical impacts on targeted individuals and communities. As social media…

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…

Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…