Publications (17)
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks
Mansi Phute, Matthew Hull, Haoran Wang +6
Deep learning models deployed in safety critical applications like autonomous driving use simulations to test their robustness against adversarial attacks in realistic conditions.…
Managing Project Teams in an Online Class of 1000+ Students
Nazanin Tabatabaei Anaraki, Taneisha Ng, Gaurav Verma +6
Team projects in Computer Science (CS) help students build collaboration skills, apply theory, and prepare for real-world software development. Online classes present unique opport…
Covariantised Vector Galileons
Matthew Hull, Kazuya Koyama, Gianmassimo Tasinato
Vector Galileons are ghost-free systems containing higher derivative interactions of vector fields. They break the vector gauge symmetry, and the dynamics of the longitudinal vecto…
Horndeski: beyond, or not beyond?
Marco Crisostomi, Matthew Hull, Kazuya Koyama +1
Determining the most general, consistent scalar tensor theory of gravity is important for building models of inflation and dark energy. In this work we investigate the number of de…
REVAMP: Automated Simulations of Adversarial Attacks on Arbitrary Objects in Realistic Scenes
Matthew Hull, Zijie J. Wang, Duen Horng Chau
Deep Learning models, such as those used in an autonomous vehicle are vulnerable to adversarial attacks where an attacker could place an adversarial object in the environment, lead…
ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Mansi Phute, Alexander Greenhalgh, Matthew Hull +8
Adversarial attacks against vision models like object detectors are often evaluated under limited conditions, leaving their performance under-characterized. Bridging simulation and…