Related papers: Cyberbullying Classifiers are Sensitive to Model-A…

Recent generative large language models (LLMs) show remarkable performance in non-English languages, but when prompted in those languages they tend to express higher harmful social biases and toxicity levels. Prior work has shown that…

Monitoring coding agents for dangerous behavior using language models requires classifying transcripts that often exceed 500K tokens, but prior agent monitoring benchmarks rarely contain transcripts longer than 100K tokens. We show that…

This paper tackles one of the greatest limitations in Machine Learning: Data Scarcity. Specifically, we explore whether high accuracy classifiers can be built from small datasets, utilizing a combination of data augmentation techniques and…

Natural Language Processing (NLP) models based on Machine Learning (ML) are susceptible to adversarial attacks -- malicious algorithms that imperceptibly modify input text to force models into making incorrect predictions. However,…

Cyberbullying is a problem in today's ubiquitous online communities. Filtering it out of online conversations has proven a challenge, and efforts have led to the creation of many different datasets, all offered as resources to train…

Adversarial Robustness is a growing field that evidences the brittleness of neural networks. Although the literature on adversarial robustness is vast, a dimension is missing in these studies: assessing how severe the mistakes are. We call…

Large language models show strong performance on knowledge intensive tasks such as fact-checking and question answering, yet they often struggle with numerical reasoning. We present a systematic evaluation of state-of-the-art models for…

Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…

Despite the recent successes of transformer-based models in terms of effectiveness on a variety of tasks, their decisions often remain opaque to humans. Explanations are particularly important for tasks like offensive language or toxicity…

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…

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…

Recent works show that text-to-image generative models are surprisingly vulnerable to a variety of poisoning attacks. Empirical results find that these models can be corrupted by altering associations between individual text prompts and…

Growing evidence shows that proactive content moderation supported by AI can help improve online discourse. However, we know little about designing these systems, how design impacts efficacy and user experience, and how people perceive…

The proliferation of online toxic speech is a pertinent problem posing threats to demographic groups. While explicit toxic speech contains offensive lexical signals, implicit one consists of coded or indirect language. Therefore, it is…

Online fake news profoundly distorts public judgment and erodes trust in social platforms. While existing detectors achieve competitive performance on benchmark datasets, they remain notably vulnerable to malicious comments designed…

Recent research has highlighted that assigning specific personas to large language models (LLMs) can significantly increase harmful content generation. However, limited attention has been given to persona-driven toxicity in non-Western…

Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial…

Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only…

Adversarial examples have proven to threaten speaker identification systems, and several countermeasures against them have been proposed. In this paper, we propose a method to detect the presence of adversarial examples, i.e., a binary…

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…