Copertina

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

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Truong, Vu Tuan, Le, Long Bao
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

PureDiffusion: Using Backdoor to Counter Backdoor in Generative Diffusion Models
di: Truong, Vu Tuan, et al.
Pubblicazione: (2024)

Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
di: Wei, Shaokui, et al.
Pubblicazione: (2024)

Backdoor Defense in Diffusion Models via Spatial Attention Unlearning
di: Jha, Abha, et al.
Pubblicazione: (2025)

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

Prototype Guided Backdoor Defense
di: Amula, Venkat Adithya, et al.
Pubblicazione: (2025)

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

BackdoorVLM: A Benchmark for Backdoor Attacks on Vision-Language Models
di: Li, Juncheng, et al.
Pubblicazione: (2025)

Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
di: Truong, Vu Tuan, et al.
Pubblicazione: (2026)

Proactive Disentangled Modeling of Trigger-Object Pairings for Backdoor Defense
di: Stein, Kyle, et al.
Pubblicazione: (2025)

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

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

BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
di: Wu, Baoyuan, et al.
Pubblicazione: (2024)

A Patch-based Cross-view Regularized Framework for Backdoor Defense in Multimodal Large Language Models
di: Fang, Tianmeng, et al.
Pubblicazione: (2026)

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

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
di: Zhu, Mingli, et al.
Pubblicazione: (2024)

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

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

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

Physical Backdoor: Towards Temperature-based Backdoor Attacks in the Physical World
di: Yin, Wen, et al.
Pubblicazione: (2024)

BackdoorIDS: Zero-shot Backdoor Detection for Pretrained Vision Encoder
di: Huang, Siquan, et al.
Pubblicazione: (2026)

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

Phantasia: Context-Adaptive Backdoors in Vision Language Models
di: Tran, Nam Duong, et al.
Pubblicazione: (2026)

Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
di: Sun, Tao, et al.
Pubblicazione: (2023)

Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models
di: Fang, Hao, et al.
Pubblicazione: (2025)

Removing the Trigger, Not the Backdoor: Alternative Triggers and Latent Backdoors
di: Abad, Gorka, et al.
Pubblicazione: (2026)

UFID: A Unified Framework for Input-level Backdoor Detection on Diffusion Models
di: Guan, Zihan, et al.
Pubblicazione: (2024)

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation
di: Aravindan, Ashwath Vaithinathan, et al.
Pubblicazione: (2025)

Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
di: Li, Boheng, et al.
Pubblicazione: (2024)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
di: Chen, Yukun, et al.
Pubblicazione: (2025)

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

Test-Time Backdoor Detection for Object Detection Models
di: Zhang, Hangtao, et al.
Pubblicazione: (2025)

Backdooring Vision-Language Models with Out-Of-Distribution Data
di: Lyu, Weimin, et al.
Pubblicazione: (2024)

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)

BOSC: A Backdoor-based Framework for Open Set Synthetic Image Attribution
di: Wang, Jun, et al.
Pubblicazione: (2024)

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

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

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

Influencer Backdoor Attack on Semantic Segmentation
di: Lan, Haoheng, et al.
Pubblicazione: (2023)