1 citations · 1 across the 2 of their papers we have counts for
4 papers
Agentic Moderation: Multi-Agent Design for Safer Vision-Language Models
Juan Ren, Mark Dras, Usman Naseem
Agentic methods have emerged as a powerful and autonomous paradigm that enhances reasoning, collaboration, and adaptive control, enabling systems to coordinate and independently so…
SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs
Juan Ren, Mark Dras, Usman Naseem
Large Vision-Language Models (LVLMs) unlock powerful multimodal reasoning but also expand the attack surface, particularly through adversarial inputs that conceal harmful goals in…
Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
Juan Ren, Mark Dras, Usman Naseem
Large Vision-Language Models (LVLMs) have shown remarkable capabilities across a wide range of multimodal tasks. However, their integration of visual inputs introduces expanded att…
POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization
Usman Naseem, Robert Geislinger, Juan Ren +40
Online polarization poses a growing challenge for democratic discourse, yet most computational social science research remains monolingual, culturally narrow, or event-specific. We…