Image de couverture de livre

When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shuai, Chao, Liu, Zhenguang, Fan, Shaojing, Gong, Bin, Lian, Weichen, Bi, Xiuli, Ba, Zhongjie, Ren, Kui
Format:	Preprint
Publié:	2026
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Harnessing Frequency Spectrum Insights for Image Copyright Protection Against Diffusion Models
par: Liu, Zhenguang, et autres
Publié: (2025)

FSFM: A Generalizable Face Security Foundation Model via Self-Supervised Facial Representation Learning
par: Wang, Gaojian, et autres
Publié: (2024)

Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
par: Ba, Zhongjie, et autres
Publié: (2024)

Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
par: Liu, Qingyu, et autres
Publié: (2026)

MixFake: Benchmarking and Enhancing Audio Deepfake Detection in Diverse Real-world Mixed Audio
par: Li, Qingcao, et autres
Publié: (2026)

R$^2$BD: A Reconstruction-Based Method for Generalizable and Efficient Detection of Fake Images
par: Liu, Qingyu, et autres
Publié: (2026)

Do As I Do: Pose Guided Human Motion Copy
par: Wu, Sifan, et autres
Publié: (2024)

WMCopier: Forging Invisible Image Watermarks on Arbitrary Images
par: Dong, Ziping, et autres
Publié: (2025)

Breaking the Generator Barrier: Disentangled Representation for Generalizable AI-Text Detection
par: Pu, Xiao, et autres
Publié: (2026)

Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation
par: Ba, Zhongjie, et autres
Publié: (2025)

SSR: Semantic and Spatial Rectification for CLIP-based Weakly Supervised Segmentation
par: Bi, Xiuli, et autres
Publié: (2025)

Morphology-optimized Multi-Scale Fusion: Combining Local Artifacts and Mesoscopic Semantics for Deepfake Detection and Localization
par: Shuai, Chao, et autres
Publié: (2025)

HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
par: Wen, Qing, et autres
Publié: (2026)

Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image Detection
par: Zhou, Yue, et autres
Publié: (2025)

"Training robust watermarking model may hurt authentication!'' Exploring and Mitigating the Identity Leakage in Robust Watermarking
par: Zhang, Xinyu, et autres
Publié: (2026)

Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
par: Wang, Yihui, et autres
Publié: (2026)

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation
par: Wang, Zhigang, et autres
Publié: (2025)

When AI companions become witty: Can human brain recognize AI-generated irony?
par: Rao, Xiaohui, et autres
Publié: (2025)

Text-CRS: A Generalized Certified Robustness Framework against Textual Adversarial Attacks
par: Zhang, Xinyu, et autres
Publié: (2023)

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation
par: Corvi, Riccardo, et autres
Publié: (2025)

Cultivating Forensic Reasoning for Generalizable Multimodal Manipulation Detection
par: Zhang, Yuchen, et autres
Publié: (2026)

Beyond Semantic Priors: Mitigating Optimization Collapse for Generalizable Visual Forensics
par: Liu, Jipeng, et autres
Publié: (2026)

Leveraging Arbitrary Data Sources for AI-Generated Image Detection Without Sacrificing Generalization
par: He, Qinghui, et autres
Publié: (2026)

Limiting the Number of Extra Dimensions with Shortcuts
par: Lin, Zi-Chao, et autres
Publié: (2023)

Optimizing Human Pose Estimation Through Focused Human and Joint Regions
par: Jiao, Yingying, et autres
Publié: (2025)

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos
par: Jiao, Yingying, et autres
Publié: (2025)

Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
par: Zhang, Haifeng, et autres
Publié: (2026)

Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection
par: Hu, Juan, et autres
Publié: (2025)

Forensics Adapter: Unleashing CLIP for Generalizable Face Forgery Detection
par: Cui, Xinjie, et autres
Publié: (2024)

Divide and Conquer: Multimodal Video Deepfake Detection via Cross-Modal Fusion and Localization
par: Li, Qingcao, et autres
Publié: (2026)

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
par: Cheng, Peng, et autres
Publié: (2024)

RedAgent: Red Teaming Large Language Models with Context-aware Autonomous Language Agent
par: Xu, Huiyu, et autres
Publié: (2024)

Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege
par: Huang, Peng, et autres
Publié: (2024)

Releasing Malevolence from Benevolence: The Menace of Benign Data on Machine Unlearning
par: Ma, Binhao, et autres
Publié: (2024)

SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution
par: Ba, Zhongjie, et autres
Publié: (2023)

I Know Who Clones Your Code: Interpretable Smart Contract Similarity Detection
par: Liu, Zhenguang, et autres
Publié: (2025)

Deepfake Forensics Adapter: A Dual-Stream Network for Generalizable Deepfake Detection
par: Liao, Jianfeng, et autres
Publié: (2026)

Physics-Aligned Spectral Mamba: Decoupling Semantics and Dynamics for Few-Shot Hyperspectral Target Detection
par: Gong, Luqi, et autres
Publié: (2026)

Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
par: Kwon, JuneHyoung, et autres
Publié: (2024)

When a Man Says He Is Pregnant: Event-related Potential Evidence for a Rational Account of Speaker-contextualized Language Comprehension
par: Wu, Hanlin, et autres
Publié: (2024)