Image de couverture de livre

A Dual-Purpose Framework for Backdoor Defense and Backdoor Amplification in Diffusion Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Truong, Vu Tuan, Le, Long Bao
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Adversarial Backdoor Defense in CLIP
par: Kuang, Junhao, et autres
Publié: (2024)

PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models
par: Truong, Vu Tuan, et autres
Publié: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
par: Wei, Shaokui, et autres
Publié: (2024)

Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
par: Jha, Abha, et autres
Publié: (2025)

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning
par: Liang, Siyuan, et autres
Publié: (2024)

Prototype Guided Backdoor Defense
par: Amula, Venkat Adithya, et autres
Publié: (2025)

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs
par: Xu, Shuhan, et autres
Publié: (2025)

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
par: Li, Juncheng, et autres
Publié: (2025)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
par: Truong, Vu Tuan, et autres
Publié: (2026)

Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
par: Stein, Kyle, et autres
Publié: (2025)

Parasite: A Steganography-based Backdoor Attack Framework for Diffusion Models
par: Chen, Jiahao, et autres
Publié: (2025)

Variance-Based Defense Against Blended Backdoor Attacks
par: Aseervatham, Sujeevan, et autres
Publié: (2025)

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
par: Wu, Baoyuan, et autres
Publié: (2024)

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
par: Fang, Tianmeng, et autres
Publié: (2026)

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models
par: Chou, Sheng-Yen, et autres
Publié: (2023)

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
par: Zhu, Mingli, et autres
Publié: (2024)

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
par: Wang, Zhongqi, et autres
Publié: (2025)

EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation
par: Wei, Tianyu, et autres
Publié: (2024)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
par: Wang, Zhongqi, et autres
Publié: (2024)

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
par: Yin, Wen, et autres
Publié: (2024)

BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder
par: Huang, Siquan, et autres
Publié: (2026)

Invisible Backdoor Attacks on Diffusion Models
par: Li, Sen, et autres
Publié: (2024)

Phantasia: Context-Adaptive Backdoors in Vision Language Models
par: Tran, Nam Duong, et autres
Publié: (2026)

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
par: Sun, Tao, et autres
Publié: (2023)

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
par: Fang, Hao, et autres
Publié: (2025)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
par: Abad, Gorka, et autres
Publié: (2026)

UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models
par: Guan, Zihan, et autres
Publié: (2024)

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
par: Aravindan, Ashwath Vaithinathan, et autres
Publié: (2025)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
par: Li, Boheng, et autres
Publié: (2024)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
par: Chen, Yukun, et autres
Publié: (2025)

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning
par: Liang, Siyuan, et autres
Publié: (2023)

Test-Time Backdoor Detection for Object Detection Models
par: Zhang, Hangtao, et autres
Publié: (2025)

Backdooring Vision-Language Models with Out-Of-Distribution Data
par: Lyu, Weimin, et autres
Publié: (2024)

Defending Text-to-image Diffusion Models: Surprising Efficacy of Textual Perturbations Against Backdoor Attacks
par: Chew, Oscar, et autres
Publié: (2024)

Gungnir: Exploiting Stylistic Features in Images for Backdoor Attacks on Diffusion Models
par: Zhang, Lei, et autres
Publié: (2025)

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
par: Wang, Jun, et autres
Publié: (2024)

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning
par: Xun, Yuan, et autres
Publié: (2024)

GuardDoor: Safeguarding Against Malicious Diffusion Editing via Protective Backdoors
par: Zeng, Yaopei, et autres
Publié: (2025)

FedDefender: Backdoor Attack Defense in Federated Learning
par: Gill, Waris, et autres
Publié: (2023)

Influencer Backdoor Attack on Semantic Segmentation
par: Lan, Haoheng, et autres
Publié: (2023)