.png){kind=icon}
.png){kind=icon}
Return
All-around forgery clues for generalizable AI-generated image detection
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2026.114661.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
<ul class="list">
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e4179">
Novel forensic–semantic framework for generalized AI-generated image detection.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e4184">
Dual-domain residual analysis efficiently extracts up-sampling artifacts in spatial and frequency domains.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e4189">
Fine-tuned vision-language model captures intrinsic high-level semantic forgery features of generative models.
</div></span></li>
<li class="react-xocs-list-item"><span class="list-label">•</span><span class="list-content">
<div class="u-margin-s-bottom" id="d1e4194">
Superior generalization performance across 30 diverse sub-datasets.
</div></span></li>
</ul>
Keywords:
AI-generated image detection
Low-level forensic traces
High-level semantic features
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
View more organizations