Preprints

• The Privacy Fallacy of Crowdsourced Fine-Tuning: Extracting Proprietary Data via Topic-Based Poisoning
  Sae Furukawa, Alina Oprea
  arXiv:2609.33985, 2026.

• Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models
  Sae Furukawa, Alina Oprea
  arXiv:2605.12264, 2026.

• Machine-Learning Enhanced Human-Error Detection in Drone-Assisted Bridge Inspections
  Ashley Song, Sae Furukawa, Zhian Zhou, Bryce Tu, Chi David Nembhard
  Preprint, 2025.

Other Research Works

• Differentially Private Federated Fine-tuning of Foundation Models for Hate Speech Detection
  Sae Furukawa
  Pomona College Senior Thesis, advised by David Kauchak and Eleanor Birrell, 2025.

• Towards the Development of a Real-Time Deepfake Audio Detection System in Communication Platforms
  Jonat John Mathew, Rakin Ahsan, Sae Furukawa, Jagdish Gautham Krishna Kumar, Huzaifa Pallan, Agamjeet Singh Padda, Sara Adamski, Madhu Reddiboina, Arjun Pankajakshan
  arXiv:2403.11778, 2024.