Your Synthetic Image Is a Confession: Trojaning Image-to-Image Generative Models for Private Input Reconstruction
Haolin Yuan, Alison Rebman, John Aucott, Yinzhi Cao
2026Year
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT ModelsJunjie Chu, Zeyang Sha, Michael Backes, Yang ZhangEMNLP 2024 · 3 citations
- Rethinking the Reverse-engineering of Trojan TriggersZhenting Wang, Kai Mei, Hailun Ding, Juan Zhai et al.NeurIPS 2022 · 75 citations
- USD: NSFW Content Detection for Text-to-Image Models via Scene GraphYuyang Zhang, Kangjie Chen, Xudong Jiang, Jiahui Wen et al.USENIX Security 2025
- Memories of Forgotten ConceptsMatan Rusanovsky, Shimon Malnick, Amir Jevnisek, Ohad Fried et al.CVPR 2025
- TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised LearningYupei Liu, Yanting Wang, Jinyuan JiaAAAI 2025
