Related papers: Beneath the Surface: Unveiling Harmful Memes with …

The pervasiveness of the dissemination of fake news through social media platforms poses critical risks to the trust of the general public, societal stability, and democratic institutions. This challenge calls for novel methodologies in…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Social media platforms have become central to modern communication, yet they also harbor offensive content that challenges platform safety and inclusivity. While prior research has primarily focused on textual indicators of offense, the…

Hateful memes pose a unique challenge for current machine learning systems because their message is derived from both text- and visual-modalities. To this effect, Facebook released the Hateful Memes Challenge, a dataset of memes with…

Social media platforms utilize Machine Learning (ML) and Artificial Intelligence (AI) powered recommendation algorithms to maximize user engagement, which can result in inadvertent exposure to harmful content. Current moderation efforts,…

Social media platforms are being increasingly used by malicious actors to share unsafe content, such as images depicting sexual activity, cyberbullying, and self-harm. Consequently, major platforms use artificial intelligence (AI) and human…

The rapid advancement of image generation technologies intensifies the demand for interpretable and robust detection methods. Although existing approaches often attain high accuracy, they typically operate as black boxes without providing…

Large language models (LLMs) undergo alignment training to avoid harmful behaviors, yet the resulting safeguards remain brittle: jailbreaks routinely bypass them, and fine-tuning on narrow domains can induce ``emergent misalignment'' that…

The dynamic expansion of social media has led to an inundation of hateful memes on media platforms, accentuating the growing need for efficient identification and removal. Acknowledging the constraints of conventional multimodal hateful…

Detecting hateful content is a challenging and important problem. Automated tools, like machine-learning models, can help, but they require continuous training to adapt to the ever-changing landscape of social media. In this work, we…

Large Language Models (LLMs) have garnered significant attention for their powerful ability in natural language understanding and reasoning. In this paper, we present a comprehensive empirical study to explore the performance of LLMs on…

Multimodal Large Language Models (MLLMs) have achieved significant advances in integrating visual and linguistic information, yet their ability to reason about complex and real-world scenarios remains limited. The existing benchmarks are…

Large Language Models (LLMs) can comply with harmful instructions, raising serious safety concerns despite their impressive capabilities. Recent work has leveraged probing-based approaches to study the separability of malicious and benign…

Internet memes are a central element of online culture, blending images and text. While substantial research has focused on either the visual or textual components of memes, little attention has been given to their interplay. This gap…

Large Language Models (LLMs) drive current AI breakthroughs despite very little being known about their internal representations. In this work, we propose to shed the light on LLMs inner mechanisms through the lens of geometry. In…

Harmful text detection has become a crucial task in the development and deployment of large language models, especially as AI-generated content continues to expand across digital platforms. This study proposes a joint retrieval framework…

The rapid advancement of deep generative models has significantly improved the realism of synthetic media, presenting both opportunities and security challenges. While deepfake technology has valuable applications in entertainment and…

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…

The rapid spread of memes makes harmful content detection increasingly crucial, as effective identification can curb the circulation of misinformation. However, existing methods rely heavily on high-volume annotated data, which leads to…

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…