$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models
Research paper by Wonwoo Choi and collaborators, published 2026 in arXiv (Cornell University). Research area: Adversarial Robustness in Machine Learning.
Resource information
- Authors
- Wonwoo Choi, Minjae Seo, Minkyoo Song, Hwanjo Heo, Seungwon Shin, Myoungsung You
- Research area
- Adversarial Robustness in Machine Learning
- Application domain
- General AI research
- AI methods
- Large language models
- Research topics
- Adversarial Robustness in Machine Learning, Digital Media Forensic Detection, Generative Adversarial Networks and Image Synthesis
- Publication date
- 2026-01-08
- Publication
- arXiv (Cornell University)
- DOI
- 10.48550/arxiv.2601.05150
- Citations
- 1
- Last record update
- Nov 5, 2026