Copertina

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chew, Oscar, Lu, Po-Yi, Lin, Jayden, Lin, Hsuan-Tien
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

PEPPER: Perception-Guided Perturbation for Robust Backdoor Defense in Text-to-Image Diffusion Models
di: Chew, Oscar, et al.
Pubblicazione: (2025)

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

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
di: Du, Lingyu, et al.
Pubblicazione: (2025)

Defending Against Frequency-Based Attacks with Diffusion Models
di: Amerehi, Fatemeh, et al.
Pubblicazione: (2025)

Projected Gradient Unlearning for Text-to-Image Diffusion Models: Defending Against Concept Revival Attacks
di: Aladawi, Aljalila, et al.
Pubblicazione: (2026)

TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
di: Zou, Quanchen, et al.
Pubblicazione: (2026)

Defending Against Repetitive Backdoor Attacks on Semi-supervised Learning through Lens of Rate-Distortion-Perception Trade-off
di: Lee, Cheng-Yi, et al.
Pubblicazione: (2024)

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

TrojVLM: Backdoor Attack Against Vision Language Models
di: Lyu, Weimin, et al.
Pubblicazione: (2024)

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
di: Chen, Jiahao, et al.
Pubblicazione: (2025)

Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation
di: Jiang, Shiyi, et al.
Pubblicazione: (2025)

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

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
di: Ishmam, Alvi Md, et al.
Pubblicazione: (2024)

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

Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
di: Iwamatsu, Shota, et al.
Pubblicazione: (2025)

Defending Against Physical Adversarial Patch Attacks on Infrared Human Detection
di: Strack, Lukas, et al.
Pubblicazione: (2023)

Expanding the Role of Diffusion Models for Robust Classifier Training
di: Huang, Pin-Han, et al.
Pubblicazione: (2026)

Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning
di: Zhang, Zhifang, et al.
Pubblicazione: (2024)

HoneypotNet: Backdoor Attacks Against Model Extraction
di: Wang, Yixu, et al.
Pubblicazione: (2025)

Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
di: Niu, Zhenxing, et al.
Pubblicazione: (2024)

Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
di: Zhou, Qi, et al.
Pubblicazione: (2024)

INK: Inheritable Natural Backdoor Attack Against Model Distillation
di: Liu, Xiaolei, et al.
Pubblicazione: (2023)

Fight Perturbations with Perturbations: Defending Adversarial Attacks via Neuron Influence
di: Chen, Ruoxi, et al.
Pubblicazione: (2021)

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

Clean-image Backdoor Attacks
di: Rong, Dazhong, et al.
Pubblicazione: (2024)

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

FedDefender: Backdoor Attack Defense in Federated Learning
di: Gill, Waris, et al.
Pubblicazione: (2023)

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
di: Yu, Yi, et al.
Pubblicazione: (2024)

Uncertainty-Aware SAR ATR: Defending Against Adversarial Attacks via Bayesian Neural Networks
di: Ye, Tian, et al.
Pubblicazione: (2024)

Defending Deepfake via Texture Feature Perturbation
di: Zhang, Xiao, et al.
Pubblicazione: (2025)

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

Time Traveling to Defend Against Adversarial Example Attacks in Image Classification
di: Etim, Anthony, et al.
Pubblicazione: (2024)

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

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

BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
di: Guo, Ji, et al.
Pubblicazione: (2025)

DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
di: Zhou, Ziqi, et al.
Pubblicazione: (2025)

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
di: Xu, Shuhan, et al.
Pubblicazione: (2025)

FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
di: Zhao, Lin, et al.
Pubblicazione: (2024)

BadVim: Unveiling Backdoor Threats in Visual State Space Model
di: Lee, Cheng-Yi, et al.
Pubblicazione: (2024)

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