Imagen de Portada

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xun, Yuan, Liang, Siyuan, Jia, Xiaojun, Liu, Xinwei, Cao, Xiaochun
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Robust Anti-Backdoor Instruction Tuning in LVLMs
por: Xun, Yuan, et al.
Publicado: (2025)

Adversarial Backdoor Defense in CLIP
por: Kuang, Junhao, et al.
Publicado: (2024)

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

PersGuard: Preventing Malicious Personalization via Backdoor Attacks on Pre-trained Text-to-Image Diffusion Models
por: Liu, Xinwei, et al.
Publicado: (2025)

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

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats
por: Liu, Kuanrong, et al.
Publicado: (2024)

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
por: Liang, Jiawei, et al.
Publicado: (2024)

GeoShield: Safeguarding Geolocation Privacy from Vision-Language Models via Adversarial Perturbations
por: Liu, Xinwei, et al.
Publicado: (2025)

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
por: Liang, Siyuan, et al.
Publicado: (2026)

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

Bridging the Task Gap: Multi-Task Adversarial Transferability in CLIP and Its Derivatives
por: Liu, Kuanrong, et al.
Publicado: (2025)

SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models
por: Wang, Haobo, et al.
Publicado: (2026)

Contrastive Learning with Counterfactual Explanations for Radiology Report Generation
por: Li, Mingjie, et al.
Publicado: (2024)

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

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models
por: Liang, Jiawei, et al.
Publicado: (2024)

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation
por: Liang, Jiawei, et al.
Publicado: (2022)

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift
por: Liang, Siyuan, et al.
Publicado: (2024)

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation
por: Lou, Tianrui, et al.
Publicado: (2025)

Towards Robust Physical-world Backdoor Attacks on Lane Detection
por: Zhang, Xinwei, et al.
Publicado: (2024)

Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks
por: Hossain, Md. Iqbal, et al.
Publicado: (2025)

Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning
por: Liu, Xinwei, et al.
Publicado: (2024)

BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP
por: Bai, Jiawang, et al.
Publicado: (2023)

Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection
por: Chen, Ruoyu, et al.
Publicado: (2025)

Does Few-shot Learning Suffer from Backdoor Attacks?
por: Liu, Xinwei, et al.
Publicado: (2023)

Semantic-aware Adversarial Fine-tuning for CLIP
por: Zhang, Jiacheng, et al.
Publicado: (2026)

Did Models Sufficient Learn? Attribution-Guided Training via Subset-Selected Counterfactual Augmentation
por: Chen, Yannan, et al.
Publicado: (2025)

Backdooring Self-Supervised Contrastive Learning by Noisy Alignment
por: Chen, Tuo, et al.
Publicado: (2025)

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
por: Lou, Tianrui, et al.
Publicado: (2024)

A Survey on Transferability of Adversarial Examples across Deep Neural Networks
por: Gu, Jindong, et al.
Publicado: (2023)

Text Adversarial Attacks with Dynamic Outputs
por: Wang, Wenqiang, et al.
Publicado: (2025)

Prototypical Contrastive Learning-based CLIP Fine-tuning for Object Re-identification
por: Li, Jiachen, et al.
Publicado: (2023)

Semantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
por: Ishmam, Alvi Md, et al.
Publicado: (2024)

Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
por: Qi, Jianhan, et al.
Publicado: (2024)

Augmented Neural Fine-Tuning for Efficient Backdoor Purification
por: Karim, Nazmul, et al.
Publicado: (2024)

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework
por: Wang, Xuan, et al.
Publicado: (2025)

F-HOI: Toward Fine-grained Semantic-Aligned 3D Human-Object Interactions
por: Yang, Jie, et al.
Publicado: (2024)

MulCLIP: A Multi-level Alignment Framework for Enhancing Fine-grained Long-context CLIP
por: Truong, Chau, et al.
Publicado: (2025)

A Visual Leap in CLIP Compositionality Reasoning through Generation of Counterfactual Sets
por: Jia, Zexi, et al.
Publicado: (2025)

CLIPVQA:Video Quality Assessment via CLIP
por: Xing, Fengchuang, et al.
Publicado: (2024)

Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images
por: Chen, Jingzhou, et al.
Publicado: (2025)