Cover Image

Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishability

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Hao, Guo, Shangwei, He, Jialing, Liu, Hangcheng, Zhang, Tianwei, Xiang, Tao
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Computer Vision and Pattern Recognition Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Disrupting Vision-Language Model-Driven Navigation Services via Adversarial Object Fusion
by: Xie, Chunlong, et al.
Published: (2025)

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

Model X-ray:Detecting Backdoored Models via Decision Boundary
by: Su, Yanghao, et al.
Published: (2024)

REDEditing: Relationship-Driven Precise Backdoor Poisoning on Text-to-Image Diffusion Models
by: Guo, Chongye, et al.
Published: (2025)

Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models
by: Yang, Ying, et al.
Published: (2025)

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
by: Zhuang, Haomin, et al.
Published: (2023)

On the Adversarial Robustness of Large Vision-Language Models under Visual Token Compression
by: Zhang, Xinwei, et al.
Published: (2026)

Backdoor Attack on Vision Language Models with Stealthy Semantic Manipulation
by: Zhong, Zhiyuan, et al.
Published: (2025)

Poisoning-based Backdoor Attacks for Arbitrary Target Label with Positive Triggers
by: Huang, Binxiao, et al.
Published: (2024)

A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
by: Li, Ziqiang, et al.
Published: (2023)

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

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
by: Yin, Ziyi, et al.
Published: (2023)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
by: Fang, Hao, et al.
Published: (2024)

Model Pairing Using Embedding Translation for Backdoor Attack Detection on Open-Set Classification Tasks
by: Unnervik, Alexander, et al.
Published: (2024)

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
by: Cheng, Siyuan, et al.
Published: (2024)

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning
by: Zhang, Jinghuai, et al.
Published: (2022)

Backdoor Attacks on Prompt-Driven Video Segmentation Foundation Models
by: Zhang, Zongmin, et al.
Published: (2025)

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization
by: Iftee, Md Akil Raihan, et al.
Published: (2025)

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

Revocable Backdoor for Deep Model Trading
by: Xu, Yiran, et al.
Published: (2024)

Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
by: Souri, Hossein, et al.
Published: (2024)

Checkerboard: A Simple, Effective, Efficient and Learning-free Clean Label Backdoor Attack with Low Poisoning Budget
by: Yang, Yi, et al.
Published: (2026)

Test-Time Attention Purification for Backdoored Large Vision Language Models
by: Zhang, Zhifang, et al.
Published: (2026)

BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning
by: Yang, Ziqing, et al.
Published: (2026)

NWaaS: Nonintrusive Watermarking as a Service for X-to-Image DNN
by: An, Haonan, et al.
Published: (2025)

IPA-NeRF: Illusory Poisoning Attack Against Neural Radiance Fields
by: Jiang, Wenxiang, et al.
Published: (2024)

Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
by: Yang, Sheng, et al.
Published: (2024)

Wicked Oddities: Selectively Poisoning for Effective Clean-Label Backdoor Attacks
by: Nguyen, Quang H., et al.
Published: (2024)

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning
by: Sun, Mengyuan, et al.
Published: (2025)

Deferred Poisoning: Making the Model More Vulnerable via Hessian Singularization
by: He, Yuhao, et al.
Published: (2024)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
by: Fu, Jiyuan, et al.
Published: (2024)

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

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

Mitigating Backdoor Attacks using Activation-Guided Model Editing
by: Hsieh, Felix, et al.
Published: (2024)

Multi-Target Federated Backdoor Attack Based on Feature Aggregation
by: Hao, Lingguag, et al.
Published: (2025)

Clean-image Backdoor Attacks
by: Rong, Dazhong, et al.
Published: (2024)

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

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

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

Event Trojan: Asynchronous Event-based Backdoor Attacks
by: Wang, Ruofei, et al.
Published: (2024)