Imagen de Portada

Boosting Active Defense Persistence: A Two-Stage Defense Framework Combining Interruption and Poisoning Against Deepfake

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zheng, Hongrui, Li, Yuezun, Wang, Liejun, Diao, Yunfeng, Guo, Zhiqing
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models
por: Zheng, Hongrui, et al.
Publicado: (2026)

DiffMark: Diffusion-based Robust Watermark Against Deepfakes
por: Sun, Chen, et al.
Publicado: (2025)

WaveGuard: Robust Deepfake Detection and Source Tracing via Dual-Tree Complex Wavelet and Graph Neural Networks
por: He, Ziyuan, et al.
Publicado: (2025)

All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark
por: Wu, Junjiang, et al.
Publicado: (2026)

Post-train Black-box Defense via Bayesian Boundary Correction
por: Wang, He, et al.
Publicado: (2023)

Bridging Semantic Logic Gaps: A Cognition Inspired Multimodal Boundary Preserving Network for Image Manipulation Localization
por: Li, Songlin, et al.
Publicado: (2025)

Forgery Guided Learning Strategy with Dual Perception Network for Deepfake Cross-domain Detection
por: Jia, Lixin, et al.
Publicado: (2025)

Boosting Adversarial Transferability Against Defenses via Multi-Scale Transformation
por: Guo, Zihong, et al.
Publicado: (2025)

Uncovering and Mitigating Destructive Multi-Embedding Attacks in Deepfake Proactive Forensics
por: Jia, Lixin, et al.
Publicado: (2025)

Beyond Fully Supervised Pixel Annotations: Scribble-Driven Weakly-Supervised Framework for Image Manipulation Localization
por: Li, Songlin, et al.
Publicado: (2025)

LoRA Patching: Exposing the Fragility of Proactive Defenses against Deepfakes
por: Qu, Zuomin, et al.
Publicado: (2025)

Similarity Memory Prior is All You Need for Medical Image Segmentation
por: Tang, Hao, et al.
Publicado: (2025)

Where the Devil Hides: Deepfake Detectors Can No Longer Be Trusted
por: Yuan, Shuaiwei, et al.
Publicado: (2025)

Exploiting Supervised Poison Vulnerability to Strengthen Self-Supervised Defense
por: Styborski, Jeremy, et al.
Publicado: (2024)

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
por: Zheng, Jingjing, et al.
Publicado: (2024)

Active Fake: DeepFake Camouflage
por: Sun, Pu, et al.
Publicado: (2024)

Anti-Reference: Universal and Immediate Defense Against Reference-Based Generation
por: Song, Yiren, et al.
Publicado: (2024)

The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution
por: Zhang, Erjian, et al.
Publicado: (2026)

Adversarially Robust AI-Generated Image Detection for Free: An Information Theoretic Perspective
por: Zhang, Ruixuan, et al.
Publicado: (2025)

Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting
por: Chen, Yang, et al.
Publicado: (2026)

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
por: Kumar, Vishesh, et al.
Publicado: (2026)

MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection
por: Hu, Mengxue, et al.
Publicado: (2025)

VALD: Multi-Stage Vision Attack Detection for Efficient LVLM Defense
por: Kadvil, Nadav, et al.
Publicado: (2026)

Variance-Based Defense Against Blended Backdoor Attacks
por: Aseervatham, Sujeevan, et al.
Publicado: (2025)

Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection
por: Lin, Yuzhen, et al.
Publicado: (2024)

A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication
por: Deng, Jingyi, et al.
Publicado: (2024)

Generalizable Face Forgery Detection via Separable Prompt Learning
por: Yang, Enrui, et al.
Publicado: (2026)

ID-Eraser: Proactive Defense Against Face Swapping via Identity Perturbation
por: Luo, Junyan, et al.
Publicado: (2026)

Defense-to-Attack: Bypassing Weak Defenses Enables Stronger Jailbreaks in Vision-Language Models
por: Zhao, Yunhan, et al.
Publicado: (2025)

Boosting Adversarial Transferability for Skeleton-based Action Recognition via Exploring the Model Posterior Space
por: Diao, Yunfeng, et al.
Publicado: (2024)

Versatile Defense Against Adversarial Attacks on Image Recognition
por: Zhang, Haibo, et al.
Publicado: (2024)

Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
por: Hufe, Lorenz, et al.
Publicado: (2025)

Struggle with Adversarial Defense? Try Diffusion
por: Li, Yujie, et al.
Publicado: (2024)

GAN-Based Single-Stage Defense for Traffic Sign Classification Under Adversarial Patch
por: Enan, Abyad, et al.
Publicado: (2025)

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
por: Choi, June Suk, et al.
Publicado: (2024)

Which Face and Whose Identity? Solving the Dual Challenge of Deepfake Proactive Forensics in Multi-Face Scenarios
por: Zhang, Lei, et al.
Publicado: (2026)

GIFGuard: Proactive Forensics against Deepfakes in Facial GIFs via Spatiotemporal Watermarking
por: Che, Shupeng, et al.
Publicado: (2026)

Steganalysis on Digital Watermarking: Is Your Defense Truly Impervious?
por: Yang, Pei, et al.
Publicado: (2024)

SIFT-Graph: Benchmarking Multimodal Defense Against Image Adversarial Attacks With Robust Feature Graph
por: He, Jingjie, et al.
Publicado: (2025)

Adversarial Backdoor Defense in CLIP
por: Kuang, Junhao, et al.
Publicado: (2024)