Portrait of Qiuyu Tang

Home

Qiuyu Tang

PhD Student in Computer Science and Engineering

Computer Science and Engineering, Lehigh University

qit220@lehigh.edu

Qiuyu Tang is a PhD student in Computer Science and Engineering at Lehigh University, advised by Dr. Aparna Bharati. Her research focuses on trustworthy visual computing, spanning media forensics, origin protection, generative image editing, and adversarial robustness. She works on methods that make image generation and editing more secure, interpretable, and reliable.

Research Interests

  • Generative Model Security
  • Media Forensics
  • Image Manipulation Detection
  • Origin Protection
  • Multimodal Learning
  • Adversarial Robustness
  • Trustworthy AI

Recent News

Highlights and updates

View all news

Mar 7, 2026

Co-organized VALED at WACV 2026

Helped organize the VALED workshop focused on Democratization vs. Copyright Dilemma in the Generative AI Era.

Sep 17, 2025

StyleProtect released as a preprint

Shared new work on protecting artistic identity in fine-tuned diffusion models.

May 20, 2025

ICIP 2025 paper accepted

Published work on effects of perturbation-based image protection on image editing.

Selected Publications

Featured recent work

Browse all output
preprint 2026

MicroFakes: A Dataset for Small but Semantically Relevant Image Manipulations

Joshua Krinsky , Qiuyu Tang , Aparna Bharati

arXiv · 2026

Introduces a dataset for small but semantically relevant image manipulations.

preprint 2026

ReVA: A New Scene-Centric Dataset for Remote Sensing Video Question Answering

Zhen Yao , Likai Wang , Yuming Yang , Zhihao Zheng , Bo Lang , Qiuyu Tang , Yuehai Yang , Jumal Barker , Mooi Choo Chuah

arXiv · 2026

Introduces a large-scale dataset for remote sensing video question answering, designed to assess spatiotemporal, scene-centric, and reasoning-oriented capabilities of MLLMs.

preprint 2026

A Survey of Origin Protection Methods against Diffusion-based Image Editing

Qiuyu Tang , Aparna Bharati

arXiv · 2026

Provides a systematic and structured overview of protection mechanisms against diffusion-based image manipulation, organized along three dimensions: threat model, victim image type, and protection paradigm.