Related papers: Harnessing Hyperbolic Geometry for Harmful Prompt …

Hateful memes have become a significant concern on the Internet, necessitating robust automated detection systems. While Large Multimodal Models (LMMs) have shown promise in hateful meme detection, they face notable challenges like…

Multimodal large language models (MLLMs) are widely used in vision-language reasoning tasks. However, their vulnerability to adversarial prompts remains a serious concern, as safety mechanisms often fail to prevent the generation of harmful…

Vision-Language Models (VLMs) have gained community-spanning prominence due to their ability to integrate visual and textual inputs to perform complex tasks. Despite their success, the internal decision-making processes of these models…

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language understanding, reasoning, and generation. However, these systems remain susceptible to malicious prompts that induce unsafe or policy-violating…

With the advent and widespread deployment of Multimodal Large Language Models (MLLMs), the imperative to ensure their safety has become increasingly pronounced. However, with the integration of additional modalities, MLLMs are exposed to…

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

Prompt injection and jailbreaking attacks pose persistent security challenges to large language model (LLM)-based systems. We present PromptScreen, an efficient and systematically evaluated defense architecture that mitigates these threats…

Large Language Models (LLMs) are increasingly equipped with capabilities of real-time web search and integrated with protocols like Model Context Protocol (MCP). This extension could introduce new security vulnerabilities. We present a…

The evolution of ransomware requires the development of more sophisticated detection methodologies capable of identifying malicious behaviors beyond traditional signature-based and heuristic techniques. The proposed Hierarchical…

The advent of social media has given rise to numerous ethical challenges, with hate speech among the most significant concerns. Researchers are attempting to tackle this problem by leveraging hate-speech detection and employing language…

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems -- using formalisms…

Manual lifting tasks are a major contributor to work-related musculoskeletal disorders, and effective ergonomic risk assessment is essential for quantifying physical exposure and informing ergonomic interventions. The Revised NIOSH Lifting…

Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and commercial concern. Existing safety evaluations predominantly rely on fixed collections of…

As language models are increasingly used in scientific workflows, evaluating their ability to propose sets of explanations-not just a single correct answer-becomes critical. Many scientific problems are underdetermined: multiple,…

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…

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Large Vision-Language Models (LVLMs) have demonstrated impressive multimodal understanding capabilities, yet they remain prone to object hallucination, where models describe non-existent objects or attribute incorrect factual information,…

In-context learning (ICL) with Large Vision Models (LVMs) presents a promising avenue in medical image segmentation by reducing the reliance on extensive labeling. However, the ICL performance of LVMs highly depends on the choices of visual…

Large Language Models (LLMs) are deployed in interactive contexts with direct user engagement, such as chatbots and writing assistants. These deployments are vulnerable to prompt injection and jailbreaking (collectively, prompt hacking), in…