HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Knowledge of the ViT backbone alone enables highly effective gray-box adversarial attacks on synthetic image detectors, often nearing white-box performance.
citing papers explorer
-
HydraPrompt: An Adaptive and Asymmetric Framework of Vision-Language Models for Synthetic Image Detection
HydraPrompt uses an Asymmetric Prompt Adapter with fixed real prompts and adaptive fake prompts plus a Conditional Supervised Contrastive loss to achieve SOTA synthetic image detection on benchmarks.
-
Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics
Knowledge of the ViT backbone alone enables highly effective gray-box adversarial attacks on synthetic image detectors, often nearing white-box performance.