文章总览 - 12
Towards Universal Fake Image Detectors That Generalize Across Generative Models
1
Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection
发表于CVPR2024,。
2
MarkDown（四）
3Incomplete Multi-View Multi-Label Learning via Label-Guided Masked View- and Category-Aware Transformers
4
Pixel-Level Anomaly Detection via Uncertainty-aware Prototypical Transformer
发表于ACM MM 2022，基于不确定性感知原型transformer，该模型同时考虑异常区域的多样性和不确定性，从而实现精准的像素级视觉异常检测。
5
ALDEN:Dual-Level Disentanglement with Meta-learning for Generalizable Audio Deepfake Detection
6
Unsupervised_Domain_Adaptation_for_Face_Anti-Spoofing
7Standing on the Shoulders of Giants:Reprogramming Visual-Language Model for General Deepfake Detection
8
Guard Me If You Know Me:Protecting Specific Face-Identity from Deepfakes
aixiv文章，基于大语言模型完成人脸篡改的检测任务，其核心的创新点是利用已知面部特征实现个性化、精准且可解释的检测框架VIPGuard。评价：其提出来一种新的MLLM的训练模式，第一阶段让MLLM正确描述人脸，第二阶段让MLLM正确区分人脸，第三阶段让MLLM正确认识给定的身份信息。 - 人脸篡改检测 - MLLM
9
Generalizable Synthetic Image Detection via Language-guided Contrastive Learning
10