Publications

ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages

Published in arXiv, 2025

Downstream models are vulnerable to blackbox attacks by 3dgs camouflages

Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haoran Wang, Matthew Lau, Wenke Lee, Willian Lunardi, Martin Andreoni, and Duen Horng Chau

arXiv

3D Gaussian Splat Vulnerabilities

Published in CVPR Workshop on Neural Fields Beyond Conventional Cameras (NFBCC), 2025

3D Gaussian splats easily attacked

Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haoran Wang, Matthew Lau, Wenke Lee, Willian Lunardi, Martin Andreoni, and Duen Horng Chau

CVPR'25

RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering

Published in International Joint Conference on Artificial Intelligence (IJCAI), 2025

A Survey on Adversarial Attacks Using Differentiable Rendering

Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling, Mansi Phute, Chao Zhang, Zsolt Kira, Willian Lunardi, Martin Andreoni, Wenke Lee, and Duen Horng Chau

IJCAI'25

Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models

Published in Neural Information Processing Systems (NeurIPS), 2024

Safety Basin phenomenon and novel metric to measure LLM finetuning safety

ShengYun Peng, Pin-Yu Chen, Matthew Hull, Duen Horng Chau

NeurIPS'24

Revamp: Automated Simulations of Adversarial Attacks on Arbitrary Objects in Realistic Scenes

Published in International Conference on Learning Representations (Tiny Papers at ICLR), 2024

Automated simulations for adversarial object attacks in realistic scenes.

Matthew Hull and Zijie J. Wang and Duen Horng Chau

ICLR'24

Download here

LLM Self Defense

Published in International Conference on Learning Representations (Tiny Papers at ICLR), 2024

LLM’s can filter out harmful content produced by themselves!

Mansi Phute, Alec Helbling, Matthew Hull, ShengYun Peng, Sebastian Szyller, Cory Cornelius, and Duen Horng Chau

ICLR'24

Download here

VisGrader: Automatic Grading of D3 Visualizations

Published in IEEE Transactions on Visualization and Computer Graphics (TVCG), 2023

Automatic grading of D3 visualizations.

Matthew Hull, Vivian Pednekar, Hannah Murray, Nimisha Roy, Emmanuel Tung, Susanta Routray, Connor Guerin, Justin Chen, Zijie J. Wang, Seongmin Lee, Mahdi Roozbahani, and Duen Horng Chau

VIS'23

Download here

Robust Principles: Architectural Design Principles for Adversarially Robust CNNs

Published in British Machine Vision Conference (BMVC), 2023

A suite of generalizable robust architectural design principles.

ShengYun Peng, Weilin Xu, Cory Cornelius, Matthew Hull, Kevin Li, Rahul Duggal, Mansi Phute, Jason Martin, and Duen Horng (Polo) Chau

BMVC'23

Download here

DetectorDetective: Investigating the Effects of Adversarial Examples on Object Detectors

Published in Conference on Computer Vision and Pattern Recognition (CVPR), 2022

Visualize Adversarial Examples on Object Detectors.

Sivapriya Vellaichamy, Matthew Hull, Zijie J Wang, Nilaksh Das, ShengYun Peng, Haekyu Park, and Duen Horng (Polo) Chau

Conference on Computer Vision and Pattern Recognition (CVPR)

Download here

Towards Automatic Grading of D3.js Visualizations

Published in IEEE Visualization Conference (VIS), 2021

Automatic Grading of D3.js Visualizations.’

Matthew Hull, Connor Guerin, Justin Chen, Susanta Routray, Duen Horng (Polo) Chau

VIS'21

Download here

Argo Lite: Open-Source Interactive Graph Exploration and Visualization in Browsers

Published in Conference on Information and Knowledge Management (CIKM), 2020

In-browser interactive graph exploration and visualization tool.

Siwei Li, Zhiyan Zhou, Anish Upadhayay, Omar Shaikh, Scott Freitas, Haekyu Park, Zijie J Wang, Susanta Routray, Matthew Hull, and Duen Horng Chau

CIKM'20

Download here