6 papers
Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Text-to-image generative models are widely deployed in creative tools and online platforms. To mitigate misuse, these systems rely on safety filters and moderation pipelines that a…
T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
Yifei Qian, Zhongliang Guo, Bowen Deng +5
Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP…
Count2Density: Crowd Density Estimation without Location-level Annotations
Mattia Litrico, Feng Chen, Michael Pound +3
Crowd density estimation is a well-known computer vision task aimed at estimating the density distribution of people in an image. The main challenge in this domain is the reliance…
Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is
Ahmed B Mustafa, Zihan Ye, Yang Lu +2
Despite significant advancements in alignment and content moderation, large language models (LLMs) and text-to-image (T2I) systems remain vulnerable to prompt-based attacks known a…
PlantDreamer: Achieving Realistic 3D Plant Models with Diffusion-Guided Gaussian Splatting
Zane K J Hartley, Lewis A G Stuart, Andrew P French +1
Recent years have seen substantial improvements in the ability to generate synthetic 3D objects using AI. However, generating complex 3D objects, such as plants, remains a consider…
3DGS-to-PC: Convert a 3D Gaussian Splatting Scene into a Dense Point Cloud or Mesh
Lewis A G Stuart, Michael P Pound
3D Gaussian Splatting (3DGS) excels at producing highly detailed 3D reconstructions, but these scenes often require specialised renderers for effective visualisation. In contrast,…