相关论文: Fortifying Toxic Speech Detectors Against Veiled T…

Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…

Large language models (LLMs) have demonstrated immense utility across various industries. However, as LLMs advance, the risk of harmful outputs increases due to incorrect or malicious instruction prompts. While current methods effectively…

Task oriented language understanding in dialog systems is often modeled using intents (task of a query) and slots (parameters for that task). Intent detection and slot tagging are, in turn, modeled using sentence classification and word…

We present a dataset and classifier for detecting the language of white supremacist extremism, a growing issue in online hate speech. Our weakly supervised classifier is trained on large datasets of text from explicitly white supremacist…

Model interpretability in toxicity detection greatly profits from token-level annotations. However, currently such annotations are only available in English. We introduce a dataset annotated for offensive language detection sourced from a…

The goal of hate speech detection is to filter negative online content aiming at certain groups of people. Due to the easy accessibility of social media platforms it is crucial to protect everyone which requires building hate speech…

The growing prevalence of speech deepfakes has raised serious concerns, particularly in real-world scenarios such as telephone fraud and identity theft. While many anti-spoofing systems have demonstrated promising performance on…

The spectacular expansion of the Internet has led to the development of a new research problem in the field of natural language processing: automatic toxic comment detection, since many countries prohibit hate speech in public media. There…

The growing importance of massive datasets used for deep learning makes robustness to label noise a critical property for classifiers to have. Sources of label noise include automatic labeling, non-expert labeling, and label corruption by…

Research in toxicity detection in natural language processing for the speech modality (audio-based) is quite limited, particularly for languages other than English. To address these limitations and lay the groundwork for truly multilingual…

Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This underscores the need for traceable TTS models-systems capable of…

Considering the importance of detecting hateful language, labeled hate speech data is expensive and time-consuming to collect, particularly for low-resource languages. Prior work has demonstrated the effectiveness of cross-lingual transfer…

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…

Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential…

The opacity in developing large language models (LLMs) is raising growing concerns about the potential contamination of public benchmarks in the pre-training data. Existing contamination detection methods are typically based on the text…

Diffusion-based speech generators are ubiquitous. These methods can generate very high quality synthetic speech and several recent incidents report their malicious use. To counter such misuse, synthetic speech detectors have been developed.…

With the widespread online social networks, hate speeches are spreading faster and causing more damage than ever before. Existing hate speech detection methods have limitations in several aspects, such as handling data insufficiency,…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

The rise of social networks has not only facilitated communication but also allowed the spread of harmful content. Although significant advances have been made in detecting toxic language in textual data, the exploration of concept-based…

Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…