Mansi Phute

16 papers A* 4A 1Journal 10Unranked 1
YearRankTypeTitle / Venue / Authors
2025 J jnl
3D Gaussian Splat Vulnerabilities.
CoRR
Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haoran Wang, Matthew Lau, Wenke Lee, Willian T. Lunardi, Martin Andreoni, Polo Chau
2025 J jnl
ComplicitSplat: Downstream Models are Vulnerable to Blackbox Attacks by 3D Gaussian Splat Camouflages.
CoRR
Matthew Hull, Haoyang Yang, Pratham Mehta, Mansi Phute, Aeree Cho, Haoran Wang, Matthew Lau, Wenke Lee, Willian T. Lunardi, Martin Andreoni, Polo Chau
2025 A* conf
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety.
EMNLP
Seongmin Lee, Aeree Cho, Grace C. Kim, Shengyun Peng, Mansi Phute, Duen Horng Chau
2025 J jnl
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety.
CoRR
Seongmin Lee, Aeree Cho, Grace C. Kim, Shengyun Peng, Mansi Phute, Duen Horng Chau
2025 A* conf
LLM Attributor: Interactive Visual Attribution for LLM Generation.
AAAI
Seongmin Lee, Zijie J. Wang, Aishwarya Chakravarthy, Alec Helbling, Shengyun Peng, Mansi Phute, Duen Horng (Polo) Chau, Minsuk Kahng
2025 A* conf
RenderBender: A Survey on Adversarial Attacks Using Differentiable Rendering.
IJCAI
Matthew Hull, Haoran Wang, Matthew Lau, Alec Helbling, Mansi Phute, Chao Zhang, Zsolt Kira, Willian T. Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau
2025 J jnl
UNDREAM: Bridging Differentiable Rendering and Photorealistic Simulation for End-to-end Adversarial Attacks.
CoRR
Mansi Phute, Matthew Hull, Haoran Wang, Alec Helbling, Shengyun Peng, Willian T. Lunardi, Martin Andreoni, Wenke Lee, Duen Horng Chau
2025 J jnl
VISOR++: Universal Visual Inputs based Steering for Large Vision Language Models.
CoRR
Ravikumar Balakrishnan, Mansi Phute
2025 J jnl
VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models.
CoRR
Mansi Phute, Ravikumar Balakrishnan
2024 J jnl
LLM Attributor: Interactive Visual Attribution for LLM Generation.
CoRR
Seongmin Lee, Zijie J. Wang, Aishwarya Chakravarthy, Alec Helbling, Shengyun Peng, Mansi Phute, Duen Horng Chau, Minsuk Kahng
2024 — conf
LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.
Tiny Papers @ ICLR
Mansi Phute, Alec Helbling, Matthew Hull, Shengyun Peng, Sebastian Szyller, Cory Cornelius, Duen Horng Chau
2024 A* conf
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors.
NeurIPS
Anisha Pal, Julia Kruk, Mansi Phute, Manognya Bhattaram, Diyi Yang, Duen Horng Chau, Judy Hoffman
2024 J jnl
Semi-Truths: A Large-Scale Dataset of AI-Augmented Images for Evaluating Robustness of AI-Generated Image detectors.
CoRR
Anisha Pal, Julia Kruk, Mansi Phute, Manognya Bhattaram, Diyi Yang, Duen Horng Chau, Judy Hoffman
2023 J jnl
LLM Self Defense: By Self Examination, LLMs Know They Are Being Tricked.
CoRR
Alec Helbling, Mansi Phute, Matthew Hull, Duen Horng Chau
2023 A conf
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs.
BMVC
Shengyun Peng, Weilin Xu, Cory Cornelius, Matthew Hull, Kevin Li, Rahul Duggal, Mansi Phute, Jason Martin, Duen Horng Chau
2023 J jnl
Robust Principles: Architectural Design Principles for Adversarially Robust CNNs.
CoRR
Shengyun Peng, Weilin Xu, Cory Cornelius, Matthew Hull, Kevin Li, Rahul Duggal, Mansi Phute, Jason Martin, Duen Horng Chau