Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle
Jiaming Zhang, Boyang Chen, Zherui Li, Fuyao Zhang, Xinyu Yan, Hong Xi Tae, Wenwen He, Xuan Wang, Siqi Guo, Junhao Dong, Kun Wang, Hanxun Huang, Yige Li, Xingjun Ma, Yang Cao, Lingjuan Lyu, Wei Yang Bryan Lim
cs.CR, cs.CV
Submitted: 2026-08-05
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SoK: Watermarking for AI-Generated Content
- Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Framework
- VIP: Visual Information Protection through Adversarial Attacks on Vision-Language Models
- Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
- Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognition
- DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
- DualTAP: A Dual-Task Adversarial Protector for Mobile MLLM Agents
- Going Grayscale: The Road to Understanding and Improving Unlearnable Examples
- Securing Biomedical Images from Unauthorized Training with Anti-Learning Perturbation
- Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations
- DeContext as Defense: Safe Image Editing in Diffusion Transformers
- Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
- Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
- Anti-Inpainting: A Proactive Defense Approach against Malicious Diffusion-based Inpainters under Unknown Conditions
- My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face Swapping
- Beauty and the Beast: Imperceptible Perturbations Against Diffusion-Based Face Swapping via Directional Attribute Editing
- Safeguarding Facial Identity against Diffusion-based Face Swapping via Cascading Pathway Disruption
- Vid-Freeze: Protecting Images from Malicious Image-to-Video Generation via Temporal Freezing
- SyncBreaker:Stage-Aware Multimodal Adversarial Attacks on Audio-Driven Talking Head Generation
- DLADiff: A Dual-Layer Defense Framework against Fine-Tuning and Zero-Shot Customization of Diffusion Models
Related papers
- SoK: AI-Augmented Binary Reversing
- Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
- Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
- Efficient Fuzzy PSI under One-Sided Assumptions
- Sealing the Audit-Runtime Gap for LLM Skills
- Token Composition: A Graph Based on EVM Logs