activity
20242026
collaborators

5 papers

cs.CV2026

Statistical Adversaries: Natural Backdoor-like Adversarial Features in Clean Vision Datasets

Paul K. Mandal, Pavan Reddy, Tristan Malatynski

Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in vision data that can behave as backd…

cs.CL2025

Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence

Paul K. Mandal, Cole Leo, Connor Hurley

Open-source intelligence provides a stream of unstructured textual data that can inform assessments of territorial control. We present CONTACT, a framework for territorial control…

cs.CL2025

When is dataset cartography ineffective? Using training dynamics does not improve robustness against Adversarial SQuAD

Paul K. Mandal

In this paper, I investigate the effectiveness of dataset cartography for extractive question answering on the SQuAD dataset. I begin by analyzing annotation artifacts in SQuAD and…

cs.LG2024

A Distributed Privacy Preserving Model for the Detection of Alzheimer's Disease

Paul K. Mandal

In the era of rapidly advancing medical technologies, the segmentation of medical data has become inevitable, necessitating the development of privacy preserving machine learning a…

cs.CV2024

Horizontal Federated Computer Vision

Paul K. Mandal, Cole Leo, Connor Hurley

In the modern world, the amount of visual data recorded has been rapidly increasing. In many cases, data is stored in geographically distinct locations and thus requires a large am…