Copertina

Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ahn, Jaesin, Jung, Heechul
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Cryptography and Security Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

NoisePrints: Distortion-Free Watermarks for Authorship in Private Diffusion Models
di: Goren, Nir, et al.
Pubblicazione: (2025)

PriSampler: Mitigating Property Inference of Diffusion Models
di: Hu, Hailong, et al.
Pubblicazione: (2023)

LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
di: Ahn, Beomjin, et al.
Pubblicazione: (2026)

FameBias: Embedding Manipulation Bias Attack in Text-to-Image Models
di: Roh, Jaechul, et al.
Pubblicazione: (2024)

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
di: Wang, Zhenting, et al.
Pubblicazione: (2023)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
di: Li, Xinfeng, et al.
Pubblicazione: (2024)

AMCR: A Framework for Assessing and Mitigating Copyright Risks in Generative Models
di: Yin, Zhipeng, et al.
Pubblicazione: (2025)

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability
di: Wang, Hao, et al.
Pubblicazione: (2024)

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models
di: Cui, Yingqian, et al.
Pubblicazione: (2023)

Robust Classification via a Single Diffusion Model
di: Chen, Huanran, et al.
Pubblicazione: (2023)

ArtistAuditor: Auditing Artist Style Pirate in Text-to-Image Generation Models
di: Du, Linkang, et al.
Pubblicazione: (2025)

FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing
di: Huang, Kai, et al.
Pubblicazione: (2024)

Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
di: Liu, Bochao, et al.
Pubblicazione: (2024)

Diffusion Soup: Model Merging for Text-to-Image Diffusion Models
di: Biggs, Benjamin, et al.
Pubblicazione: (2024)

SLICE: Semantic Latent Injection via Compartmentalized Embedding for Image Watermarking
di: Gao, Zheng, et al.
Pubblicazione: (2026)

Embedding Non-Distortive Cancelable Face Template Generation
di: Zakharov, Dmytro, et al.
Pubblicazione: (2024)

©Plug-in Authorization for Human Content Copyright Protection in Text-to-Image Model
di: Zhou, Chao, et al.
Pubblicazione: (2024)

Mitigating the Impact of Noisy Edges on Graph-Based Algorithms via Adversarial Robustness Evaluation
di: Wang, Yongyu, et al.
Pubblicazione: (2024)

Identifying Models Behind Text-to-Image Leaderboards
di: Naseh, Ali, et al.
Pubblicazione: (2026)

PrivImage: Differentially Private Synthetic Image Generation using Diffusion Models with Semantic-Aware Pretraining
di: Li, Kecen, et al.
Pubblicazione: (2023)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
di: Chou, Sheng-Yen, et al.
Pubblicazione: (2023)

DiffMI: Breaking Face Recognition Privacy via Diffusion-Driven Training-Free Model Inversion
di: Wang, Hanrui, et al.
Pubblicazione: (2025)

On the Multi-modal Vulnerability of Diffusion Models
di: Yang, Dingcheng, et al.
Pubblicazione: (2024)

Invisible Backdoor Attacks on Diffusion Models
di: Li, Sen, et al.
Pubblicazione: (2024)

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
di: Souri, Hossein, et al.
Pubblicazione: (2024)

Shallow Diffuse: Robust and Invisible Watermarking through Low-Dimensional Subspaces in Diffusion Models
di: Li, Wenda, et al.
Pubblicazione: (2024)

Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
di: Shpilevskiy, Frederick, et al.
Pubblicazione: (2025)

Diffence: Fencing Membership Privacy With Diffusion Models
di: Peng, Yuefeng, et al.
Pubblicazione: (2023)

Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive Smoothing
di: Qi, Leyi, et al.
Pubblicazione: (2026)

Extracting Training Data from Unconditional Diffusion Models
di: Chen, Yunhao, et al.
Pubblicazione: (2024)

Identity-Focused Inference and Extraction Attacks on Diffusion Models
di: Vora, Jayneel, et al.
Pubblicazione: (2024)

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
di: Li, Jiachen, et al.
Pubblicazione: (2025)

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models
di: Jiang, Tanqiu, et al.
Pubblicazione: (2025)

SIDE: Surrogate Conditional Data Extraction from Diffusion Models
di: Chen, Yunhao, et al.
Pubblicazione: (2024)

Unstable Unlearning: The Hidden Risk of Concept Resurgence in Diffusion Models
di: Suriyakumar, Vinith M., et al.
Pubblicazione: (2024)

DisDet: Exploring Detectability of Backdoor Attack on Diffusion Models
di: Sui, Yang, et al.
Pubblicazione: (2024)

Attention Shift: Steering AI Away from Unsafe Content
di: Garg, Shivank, et al.
Pubblicazione: (2024)

SSL-Cleanse: Trojan Detection and Mitigation in Self-Supervised Learning
di: Zheng, Mengxin, et al.
Pubblicazione: (2023)

The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models
di: Dolatabadi, Hadi M., et al.
Pubblicazione: (2023)

Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models
di: Mendieta, Matias, et al.
Pubblicazione: (2024)