Imagen de Portada

PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xu, Yukai, Gu, Yujie, Sakurai, Kouichi
Formato:	Preprint
Publicado:	2024
Materias:	Cryptography and Security Artificial Intelligence Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Data Free Backdoor Attacks
por: Cao, Bochuan, et al.
Publicado: (2024)

FLARE: Toward Universal Dataset Purification against Backdoor Attacks
por: Hou, Linshan, et al.
Publicado: (2024)

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

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

Backdoor Attacks against Image-to-Image Networks
por: Jiang, Wenbo, et al.
Publicado: (2024)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
por: Li, Jiayu, et al.
Publicado: (2025)

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

Backdoor Attack Against Vision Transformers via Attention Gradient-Based Image Erosion
por: Guo, Ji, et al.
Publicado: (2024)

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

PuriDefense: Randomized Local Implicit Adversarial Purification for Defending Black-box Query-based Attacks
por: Guo, Ping, et al.
Publicado: (2024)

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

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
por: Lu, Jialin, et al.
Publicado: (2024)

AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection
por: Lu, Jialin, et al.
Publicado: (2025)

BadViM: Backdoor Attack against Vision Mamba
por: Wu, Yinghao, et al.
Publicado: (2025)

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
por: Stein, Kyle, et al.
Publicado: (2024)

CatchBackdoor: Backdoor Detection via Critical Trojan Neural Path Fuzzing
por: Jin, Haibo, et al.
Publicado: (2021)

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
por: Zhang, Chenyu, et al.
Publicado: (2024)

Autoencoder-based Denoising Defense against Adversarial Attacks on Object Detection
por: Song, Min Geun, et al.
Publicado: (2025)

Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations
por: Pang, Lu, et al.
Publicado: (2024)

DeMark: A Query-Free Black-Box Attack on Deepfake Watermarking Defenses
por: Song, Wei, et al.
Publicado: (2026)

Differentially Private Fine-Tuning of Diffusion Models
por: Tsai, Yu-Lin, et al.
Publicado: (2024)

Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems
por: Guo, Zhongliang, et al.
Publicado: (2025)

Cert-SSBD: Certified Backdoor Defense with Sample-Specific Smoothing Noises
por: Qiao, Ting, et al.
Publicado: (2025)

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
por: Zhang, Chenyu, et al.
Publicado: (2025)

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses
por: Li, Xiao, et al.
Publicado: (2026)

Backdoor Attacks on Deep Learning Face Detection
por: Roux, Quentin Le, et al.
Publicado: (2025)

Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
por: Dunnett, Kealan, et al.
Publicado: (2026)

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
por: Zhu, Mingyan, et al.
Publicado: (2023)

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning
por: Liu, Tao, et al.
Publicado: (2024)

A Robust Attack: Displacement Backdoor Attack
por: Li, Yong, et al.
Publicado: (2025)

Backdoor Attack with Mode Mixture Latent Modification
por: Zhang, Hongwei, et al.
Publicado: (2024)

Better Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
por: Yang, Wenhan, et al.
Publicado: (2023)

Backdooring Outlier Detection Methods: A Novel Attack Approach
por: Taghavi, ZeinabSadat, et al.
Publicado: (2024)

Effective Fine-Tuning of Vision Transformers with Low-Rank Adaptation for Privacy-Preserving Image Classification
por: Lin, Haiwei, et al.
Publicado: (2025)

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
por: Jang, Sangwon, et al.
Publicado: (2025)

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

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
por: Jindal, Akshit, et al.
Publicado: (2026)

SoK: On the Survivability of Backdoor Attacks on Unconstrained Face Recognition Systems
por: Roux, Quentin Le, et al.
Publicado: (2025)

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
por: Chen, Yukun, et al.
Publicado: (2025)

NoiseAttack: An Evasive Sample-Specific Multi-Targeted Backdoor Attack Through White Gaussian Noise
por: Miah, Abdullah Arafat, et al.
Publicado: (2024)