collaborators

7 papers

cs.CV2026

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…

cs.CR2026

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.…

cs.CL2025

Superficial Self-Improved Reasoners Benefit from Model Merging

Xiangchi Yuan, Chunhui Zhang, Zheyuan Liu +4

As scaled language models (LMs) approach human-level reasoning capabilities, self-improvement emerges as a solution to synthesizing high-quality data corpus. While previous researc…

cs.CV2025

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

Matthew Hull, Haoyang Yang, Pratham Mehta +8

As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause h…

stat.ML2025

Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomalies

Matthew Lau, Tian-Yi Zhou, Xiangchi Yuan +3

Anomaly detection (AD) is a critical task across domains such as cybersecurity and healthcare. In the unsupervised setting, an effective and theoretically-grounded principle is to…

cs.CR2025

3D Gaussian Splat Vulnerabilities

Matthew Hull, Haoyang Yang, Pratham Mehta +8

With 3D Gaussian Splatting (3DGS) being increasingly used in safety-critical applications, how can an adversary manipulate the scene to cause harm? We introduce CLOAK, the first at…