Copertina

PersGuard: Preventing Malicious Personalization via Backdoor Attacks on Pre-trained Text-to-Image Diffusion Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Xinwei, Jia, Xiaojun, Xun, Yuan, Zhang, Hua, Cao, Xiaochun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Robust Anti-Backdoor Instruction Tuning in LVLMs
di: Xun, Yuan, et al.
Pubblicazione: (2025)

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
di: Xun, Yuan, et al.
Pubblicazione: (2024)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
di: Liu, Xinwei, et al.
Pubblicazione: (2025)

GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
di: Zeng, Yaopei, et al.
Pubblicazione: (2025)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
di: Liang, Jiawei, et al.
Pubblicazione: (2024)

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
di: Wang, Haobo, et al.
Pubblicazione: (2026)

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
di: Liang, Siyuan, et al.
Pubblicazione: (2024)

Does Few-shot Learning Suffer from Backdoor Attacks?
di: Liu, Xinwei, et al.
Pubblicazione: (2023)

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations
di: Li, Yanjie, et al.
Pubblicazione: (2025)

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
di: Wu, Jia, et al.
Pubblicazione: (2025)

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

ToxicTextCLIP: Text-Based Poisoning and Backdoor Attacks on CLIP Pre-training
di: Yao, Xin, et al.
Pubblicazione: (2025)

Exploring Pre-trained Text-to-Video Diffusion Models for Referring Video Object Segmentation
di: Zhu, Zixin, et al.
Pubblicazione: (2024)

EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation
di: Wei, Tianyu, et al.
Pubblicazione: (2024)

BlackMirror: Black-Box Backdoor Detection for Text-to-Image Models via Instruction-Response Deviation
di: Li, Feiran, et al.
Pubblicazione: (2026)

Restoring Images in Adverse Weather Conditions via Histogram Transformer
di: Sun, Shangquan, et al.
Pubblicazione: (2024)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
di: Zhang, Jie, et al.
Pubblicazione: (2025)

Text Adversarial Attacks with Dynamic Outputs
di: Wang, Wenqiang, et al.
Pubblicazione: (2025)

PromptGuard: Soft Prompt-Guided Unsafe Content Moderation for Text-to-Image Models
di: Yuan, Lingzhi, et al.
Pubblicazione: (2025)

DDAP: Dual-Domain Anti-Personalization against Text-to-Image Diffusion Models
di: Yang, Jing, et al.
Pubblicazione: (2024)

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
di: Liang, Jiawei, et al.
Pubblicazione: (2024)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
di: Liang, Siyuan, et al.
Pubblicazione: (2024)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
di: Liang, Siyuan, et al.
Pubblicazione: (2023)

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

Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger
di: Yu, Yi, et al.
Pubblicazione: (2024)

GCP: Guarded Collaborative Perception with Spatial-Temporal Aware Malicious Agent Detection
di: Tao, Yihang, et al.
Pubblicazione: (2025)

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2025)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
di: Wang, Zhongqi, et al.
Pubblicazione: (2024)

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
di: Chen, Ruidong, et al.
Pubblicazione: (2025)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
di: Chew, Oscar, et al.
Pubblicazione: (2024)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
di: Zhang, Lei, et al.
Pubblicazione: (2025)

Real-time Identity Defenses against Malicious Personalization of Diffusion Models
di: Guo, Hanzhong, et al.
Pubblicazione: (2024)

JeDi: Joint-Image Diffusion Models for Finetuning-Free Personalized Text-to-Image Generation
di: Zeng, Yu, et al.
Pubblicazione: (2024)

Adversarial Backdoor Defense in CLIP
di: Kuang, Junhao, et al.
Pubblicazione: (2024)

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

Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
di: Yang, Chenyu, et al.
Pubblicazione: (2024)

HTS-Attack: Heuristic Token Search for Jailbreaking Text-to-Image Models
di: Gao, Sensen, et al.
Pubblicazione: (2024)

Towards Robust Physical-world Backdoor Attacks on Lane Detection
di: Zhang, Xinwei, et al.
Pubblicazione: (2024)

Universal Image Restoration Pre-training via Degradation Classification
di: Hu, JiaKui, et al.
Pubblicazione: (2025)

A Survey on Transferability of Adversarial Examples across Deep Neural Networks
di: Gu, Jindong, et al.
Pubblicazione: (2023)