5 citations · 12 across the 16 of their papers we have counts for
21 papers
From Sharp Eyes to Expert Mind: Internalizing Expert Knowledge in MLLMs for Tampered Text Detection
Kaiqing Lin, Songze Li, Shen Chen +8
Tampered Text Detection (TTD) is essential for safeguarding document authenticity in security-critical workflows. Existing expert models are effective at capturing subtle manipulat…
ReNFT: Repairing Mode Collapse in Reward Post-Training via Internal Probability-Mass Recalibration
Yuchen Bao, Chao Wen, Haowei Wang +10
Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases within-prompt diversity. Existing m…
LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals
Haozhen Yan, Ruoxin Chen, Jiahui Zhan +6
Modern generators faithfully model macroscopic semantics, producing synthetic images that appear highly realistic. Consequently, decisive forensic cues reside in subtle non-semanti…
Deep Residual Injection for Full-Spectrum Forensic Signal Perception in Multimodal Large Language Models
Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen +8
Multimodal large language models (MLLMs) have been increasingly adopted in forensics for their robust semantic understanding. As AI-generated images become realistic, semantic-leve…
GenShield: Unified Detection and Artifact Correction for AI-Generated Images
Zhipei Xu, Xuanyu Zhang, Youmin Xu +5
Diffusion-based image synthesis has made AI-generated images (AIGI) increasingly photorealistic, raising urgent concerns about authenticity in applications such as misinformation d…
VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection
Hui Han, Shunli Wang, Yandan Zhao +2
In Deepfake Detection (DFD) tasks, researchers proposed two types of MLLM-based methods: complementary combination with small DFD detectors, or static forgery knowledge injection.…
ForgeryVCR: Visual-Centric Reasoning via Efficient Forensic Tools in MLLMs for Image Forgery Detection and Localization
Youqi Wang, Shen Chen, Haowei Wang +6
Existing Multimodal Large Language Models (MLLMs) for image forgery detection and localization predominantly operate under a text-centric Chain-of-Thought (CoT) paradigm. However,…
Align, Don't Blend: Orthogonal Supervision Disentanglement As the Key to Generalizable AI-Generated Image Detection
Ruoxin Chen, Jiahui Gao, Kaiqing Lin +5
Recent advances in AI-Generated Image (AIGI) detection have largely focused on model architectures, loss design, and training strategies, while overlooking a more fundamental facto…
TripleFDS: Triple Feature Disentanglement and Synthesis for Scene Text Editing
Yuchen Bao, Yiting Wang, Wenjian Huang +5
Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text styl…
Seeing Before Reasoning: A Unified Framework for Generalizable and Explainable Fake Image Detection
Kaiqing Lin, Zhiyuan Yan, Ruoxin Chen +7
Detecting AI-generated images with multimodal large language models (MLLMs) has gained increasing attention, due to their rich world knowledge, common-sense reasoning, and potentia…
Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes
Kaiqing Lin, Zhiyuan Yan, Ke-Yue Zhang +7
Securing personal identity against deepfake attacks is increasingly critical in the digital age, especially for celebrities and political figures whose faces are easily accessible…
Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable
Ruoxin Chen, Junwei Xi, Zhiyuan Yan +8
Existing detectors are often trained on biased datasets, leading to the possibility of overfitting on non-causal image attributes that are spuriously correlated with real/synthetic…
All Patches Matter, More Patches Better: Enhance AI-Generated Image Detection via Panoptic Patch Learning
Zheng Yang, Ruoxin Chen, Zhiyuan Yan +8
The exponential growth of AI-generated images (AIGIs) underscores the urgent need for robust and generalizable detection methods. In this paper, we establish two key principles for…
Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection
Zhiyuan Yan, Jiangming Wang, Peng Jin +7
AI-generated images (AIGIs), such as natural or face images, have become increasingly important yet challenging. In this paper, we start from a new perspective to excavate the reas…
A Quality-Centric Framework for Generic Deepfake Detection
Wentang Song, Zhiyuan Yan, Yuzhen Lin +6
Detecting AI-generated images, particularly deepfakes, has become increasingly crucial, with the primary challenge being the generalization to previously unseen manipulation method…
Decoupled Data Augmentation for Improving Image Classification
Ruoxin Chen, Zhe Wang, Ke-Yue Zhang +5
Recent advancements in image mixing and generative data augmentation have shown promise in enhancing image classification. However, these techniques face the challenge of balancing…
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
Ke Sun, Shen Chen, Taiping Yao +4
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often str…
Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning
Zhiyuan Yan, Yandan Zhao, Shen Chen +5
Three key challenges hinder the development of current deepfake video detection: (1) Temporal features can be complex and diverse: how can we identify general temporal artifacts to…
Rank-based No-reference Quality Assessment for Face Swapping
Xinghui Zhou, Wenbo Zhou, Tianyi Wei +5
Face swapping has become a prominent research area in computer vision and image processing due to rapid technological advancements. The metric of measuring the quality in most face…
DF40: Toward Next-Generation Deepfake Detection
Zhiyuan Yan, Taiping Yao, Shen Chen +8
We propose a new comprehensive benchmark to revolutionize the current deepfake detection field to the next generation. Predominantly, existing works identify top-notch detection al…
Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation
Shengming Li, Guangcong Zheng, Hui Wang +4
Denoising Diffusion Probabilistic Model (DDPM) is able to make flexible conditional image generation from prior noise to real data, by introducing an independent noise-aware classi…