Related papers: ContiGuard: A Framework for Continual Toxicity Det…

Multimodal learning systems often face substantial uncertainty due to noisy data, low-quality labels, and heterogeneous modality characteristics. These issues become especially critical in human-computer interaction settings, where data…

Since open social platforms allow for a large and continuous flow of unverified information, rumors can emerge unexpectedly and spread quickly. However, existing rumor detection (RD) models often assume the same training and testing…

Recent advances in large language models (LLMs) have demonstrated strong performance on simple text classification tasks, frequently under zero-shot settings. However, their efficacy declines when tackling complex social media challenges…

Despite the remarkable generation capabilities of diffusion models, recent studies have shown that they can memorize and create harmful content when given specific text prompts. Although fine-tuning approaches have been developed to…

Social media platforms, despite their value in promoting open discourse, are often exploited to spread harmful content. Current deep learning and natural language processing models used for detecting this harmful content overly rely on…

Social media platforms provide an environment where people can freely engage in discussions. Unfortunately, they also enable several problems, such as online harassment. Recently, Google and Jigsaw started a project called Perspective,…

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

While deep neural networks have been achieving state-of-the-art performance across a wide variety of applications, their vulnerability to adversarial attacks limits their widespread deployment for safety-critical applications. Alongside…

While continuous diffusion has shown remarkable success in continuous domains such as image generation, its direct application to discrete data has underperformed compared to purely discrete formulations. This gap is counterintuitive, given…

Recently, the new ciphertext side channels resulting from the deterministic memory encryption in Trusted Execution Environments (TEEs), enable ciphertexts to manifest identifiable patterns when being sequentially written to the same memory…

This paper presents a real-time modular defense system named Sentra-Guard. The system detects and mitigates jailbreak and prompt injection attacks targeting large language models (LLMs). The framework uses a hybrid architecture with…

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

The rapid proliferation of AI-generated text online is profoundly reshaping the information landscape. Among various types of AI-generated text, AI-generated news presents a significant threat as it can be a prominent source of…

The rapid progress of generative AI has enabled remarkable creative capabilities, yet it also raises urgent concerns regarding the safety of AI-generated visual content in real-world applications such as content moderation, platform…

Cognitive diagnosis is an essential research topic in intelligent education, aimed at assessing the level of mastery of different skills by students. So far, many research works have used deep learning models to explore the complex…

Large vision-language models (LVLMs) are increasingly used for tasks where detecting multimodal harmful content is crucial, such as online content moderation. However, real-world harmful content is often camouflaged, relying on nuanced…

In the evolving landscape of Federated Learning (FL), the challenge of ensuring data integrity against poisoning attacks is paramount, particularly for applications demanding stringent privacy preservation. Traditional anomaly detection…

Diffusion-based models have gained significant popularity for text-to-image generation due to their exceptional image-generation capabilities. A risk with these models is the potential generation of inappropriate content, such as biased or…

Adversarial attacks on Natural Language Processing (NLP) models expose vulnerabilities by introducing subtle perturbations to input text, often leading to misclassification while maintaining human readability. Existing methods typically…