You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<a><b>PromptFlare: Prompt-Generalized Defense via Cross-Attention Decoy in Diffusion-Based Inpainting</b></a>
67
+
</tr>
68
+
</thead>
69
+
<tbody>
70
+
<tr>
71
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>Hohyun Na, Seunghoo Hong and <i><b>Simon S. Woo*</b> </i> </small> </p>
72
+
</tr>
73
+
<tr>
74
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small> <b><a href="https://acmmm2025.org/"> MM '25: Proceedings of the 33nd ACM International Conference on Multimedia, Dublin, Ireland </a></b> </small> </p>
<font color='blue'>(Accepted) BK Computer Science 최우수학회 IF=4 </font>
79
+
</b> </small> </p>
80
+
</tr>
81
+
<tr>
82
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>The success of diffusion models has enabled effortless, high-quality image modifications that precisely align with users' intentions, thereby raising concerns about their potential misuse by malicious actors. Previous studies have attempted to mitigate such misuse through adversarial attacks. However, these approaches heavily rely on image-level inconsistencies, which pose fundamental limitations in addressing the influence of textual prompts. In this paper, we propose PromptFlare, a novel adversarial protection method designed to protect images from malicious modifications facilitated by diffusion-based inpainting models. Our approach leverages the cross-attention mechanism to exploit the intrinsic properties of prompt embeddings. Specifically, we identify and target shared token of prompts that are invariant and semantically uninformative, injecting adversarial noise to suppress the sampling process. Extensive experiments on the EditBench dataset demonstrate that our method achieves state-of-the-art performance across various CLIP-based and traditional metrics while significantly reducing computational overhead and GPU memory usage. These findings highlight PromptFlare as a robust and efficient protection against unauthorized image manipulations. </small> </p>
<a><b>SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection</b></a>
101
+
</tr>
102
+
</thead>
103
+
<tbody>
104
+
<tr>
105
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>Inzamamul Alam, Md Tanvir Islam and <i><b>Simon S. Woo*</b> </i> </small> </p>
106
+
</tr>
107
+
<tr>
108
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small> <b><a href="https://acmmm2025.org/"> MM '25: Proceedings of the 33nd ACM International Conference on Multimedia, Dublin, Ireland </a></b> </small> </p>
<font color='blue'>(Accepted) BK Computer Science 최우수학회 IF=4 </font>
113
+
</b> </small> </p>
114
+
</tr>
115
+
<tr>
116
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>The increasing realism of content generated by GANs and diffusion models has made deepfake detection significantly more challenging. Existing approaches often focus solely on spatial or frequency-domain features, limiting their generalization to unseen manipulations. We propose the Spectral Cross-Attentional Network (SpecXNet), a dual-domain architecture for robust deepfake detection. The core \textbf{Dual-Domain Feature Coupler (DDFC)} decomposes features into a local spatial branch for capturing texture-level anomalies and a global spectral branch that employs Fast Fourier Transform to model periodic inconsistencies. This dual-domain formulation allows SpecXNet to jointly exploit localized detail and global structural coherence, which are critical for distinguishing authentic from manipulated images. We also introduce the \textbf{Dual Fourier Attention (DFA)} module, which dynamically fuses spatial and spectral features in a content-aware manner. Built atop a modified XceptionNet backbone, we embed the DDFC and DFA modules within a separable convolution block. Extensive experiments on multiple deepfake benchmarks show that SpecXNet achieves state-of-the-art accuracy, particularly under cross-dataset and unseen manipulation scenarios, while maintaining real-time feasibility. Our results highlight the effectiveness of unified spatial-spectral learning for robust and generalizable deepfake detection. </small> </p>
<a><b>Combating Dataset Misalignment for Robust AI-Generated Image Detection in the Real World</b></a>
135
+
</tr>
136
+
</thead>
137
+
<tbody>
138
+
<tr>
139
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>Hyeongjun Choi, Inho Jung and <i><b>Simon S. Woo*</b> </i> </small> </p>
140
+
</tr>
141
+
<tr>
142
+
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small> <b><a href="https://sites.google.com/view/wdc-2025/home?authuser=0"> The 4th Workshop on the security implications of Deepfakes and Cheapfakes (WDC '25) Hanoi, Vietnam, August 2025 </a></b> </small> </p>
<p style="margin-top: 0px;margin-bottom: 0px;text-align: justify;"> <small>AI-generated images are increasingly prevalent on the web, raising concerns about the real-world applicability of detection methods. While current detectors perform well on benchmark datasets, they suffer significant performance degradation on real-world datasets. Misalignment within benchmark datasets, caused by discrepancies in how data from different classes are encoded or transformed, leads models to learn shortcuts. These shortcuts make detectors overly reliant on factors such as image compression, causing biased predictions of real-world images that inevitably undergo compression. In this work, we reveal the misalignment in widely used benchmark datasets and demonstrate that aligning datasets improves model robustness and generalizability. Additionally, we propose leveraging pre-trained visual encoders to further enhance performance in real-world scenarios. Our approach achieves significant performance gains, highlighting the importance of dataset alignment for real-world AI-generated image detection.</small> </p>
0 commit comments