Cover Image

Detecting Backdoor Samples in Contrastive Language Image Pretraining

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Hanxun, Erfani, Sarah, Li, Yige, Ma, Xingjun, Bailey, James
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP
by: Huang, Hanxun, et al.
Published: (2025)

Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
by: Cui, Kaiyuan, et al.
Published: (2026)

LDReg: Local Dimensionality Regularized Self-Supervised Learning
by: Huang, Hanxun, et al.
Published: (2024)

Density-Aware Translation of Spurious Correlations in Zero-Shot VLMs
by: Hasanebrahimi, Afsaneh, et al.
Published: (2026)

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

End-to-End Anti-Backdoor Learning on Images and Time Series
by: Jiang, Yujing, et al.
Published: (2024)

Towards Million-Scale Adversarial Robustness Evaluation With Stronger Individual Attacks
by: Xie, Yong, et al.
Published: (2024)

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks
by: Zhao, Yunhan, et al.
Published: (2024)

Concept-Aware Batch Sampling Improves Language-Image Pretraining
by: Ghosh, Adhiraj, et al.
Published: (2025)

Test-Time Multimodal Backdoor Detection by Contrastive Prompting
by: Niu, Yuwei, et al.
Published: (2024)

AIM: Additional Image Guided Generation of Transferable Adversarial Attacks
by: Li, Teng, et al.
Published: (2025)

Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
by: Joshi, Siddharth, et al.
Published: (2024)

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding
by: Mao, Ye, et al.
Published: (2026)

Be Persistent: Towards a Unified Solution for Mitigating Shortcuts in Deep Learning
by: Dolatabadi, Hadi M., et al.
Published: (2024)

SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network
by: Lv, Changze, et al.
Published: (2023)

AmorLIP: Efficient Language-Image Pretraining via Amortization
by: Sun, Haotian, et al.
Published: (2025)

Region-centric Image-Language Pretraining for Open-Vocabulary Detection
by: Kim, Dahun, et al.
Published: (2023)

WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection
by: Zi, Bojia, et al.
Published: (2021)

The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models
by: Dolatabadi, Hadi M., et al.
Published: (2023)

DDA: Dimensionality Driven Augmentation Search for Contrastive Learning in Laparoscopic Surgery
by: Zhou, Yuning, et al.
Published: (2024)

Negative Label Guided OOD Detection with Pretrained Vision-Language Models
by: Jiang, Xue, et al.
Published: (2024)

Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP
by: Jin, Ruinan, et al.
Published: (2024)

Contrastive Localized Language-Image Pre-Training
by: Chen, Hong-You, et al.
Published: (2024)

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models
by: Li, Jinhao, et al.
Published: (2024)

Modeling Caption Diversity in Contrastive Vision-Language Pretraining
by: Lavoie, Samuel, et al.
Published: (2024)

$\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs
by: Sobal, Vlad, et al.
Published: (2024)

Walnut Detection Through Deep Learning Enhanced by Multispectral Synthetic Images
by: Fu, Kaiming, et al.
Published: (2023)

Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
by: Chu, Tianzhe, et al.
Published: (2023)

Learning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
by: Khanna, Sameer, et al.
Published: (2024)

TRACER: Persistent Regularization for Robust Multimodal Finetuning
by: Asadollahzadeh, Hesam, et al.
Published: (2026)

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance
by: Lin, Miao, et al.
Published: (2026)

VAGUEGAN: Stealthy Poisoning and Backdoor Attacks on Image Generative Pipelines
by: Faisal, Mostafa Mohaimen Akand, et al.
Published: (2025)

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

Spatiotemporal Satellite Image Downscaling with Transfer Encoders and Autoregressive Generative Models
by: Xiang, Yang, et al.
Published: (2025)

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

D4C: Data-Free Quantization for Contrastive Language-Image Pre-training Models
by: Zhang, Wenlun, et al.
Published: (2025)

Stochastic Siamese MAE Pretraining for Longitudinal Medical Images
by: Emre, Taha, et al.
Published: (2025)

Pretrained Image-Text Models are Secretly Video Captioners
by: Zhang, Chunhui, et al.
Published: (2025)

Time-to-Event Pretraining for 3D Medical Imaging
by: Huo, Zepeng, et al.
Published: (2024)

DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks
by: Vartak, Akash, et al.
Published: (2025)