Author

Mansi Phute

h-index 6 View on Semantic Scholar

We have 3 of 17 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Aug 2025

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

ComplicitSplat is introduced, the first attack that exploits standard 3DGS shading methods to create viewpoint-specific camouflage to embed adversarial content in scene objects that are visible only from specific viewpoints and without requiring access to model architecture or weights.

Matthew Hull, Haoyang Yang, P. Mehta et al. · arXiv.org · 1 citation

Jul 2026

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments

Through ALLUDE's end-to-end differentiable rendering, adversarial attacks can be optimized against shifting real-world deployment conditions, and can be optimized against shifting real-world deployment conditions.

Mansi Phute, Alexander D. Greenhalgh, Matthew Hull et al. · arXiv.org · 0 citations

#machine learning Preprint Aug 2026

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity

Adversarial Robustness with Manifold-Oriented Training (ARMOR), a novel defense that realizes the core insights of on-manifold adversarial training (OMAT) in low-data regimes and translates insights from manifold-based training to defend object detectors amidst training data scarcity.

Hao-Ran Wang, Matthew Lau, Alec Helbling et al. · 0 citations