The one-stop shop, including all posts from the Blog, Monthly Music, and Projects.
2025
- UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks papers
- VISOR++ - Transferrable Visual Input based Steering for Output Redirection in Large Vision Language Models papers
- VISOR - Visual Input based Steering for Output Redirection in Large Vision Language Models papers
- ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages papers
- 3D Gaussian Splat Vulnerabilities papers
- Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety papers
- RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering papers
2024
- Semi Truths: A Large-Scale Dataset for Testing Robustness of AI-Generated Image Detectors papers
- LLM Attributor: Interactive Visual Attribution for LLM Generation papers