Cover Image

Robust Defense Strategies for Multimodal Contrastive Learning: Efficient Fine-tuning Against Backdoor Attacks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hossain, Md. Iqbal, Sajeeda, Afia, Perla, Neeresh Kumar, Shao, Ming
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

Securing Vision-Language Models with a Robust Encoder Against Jailbreak and Adversarial Attacks
by: Hossain, Md Zarif, et al.
Published: (2024)

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

Towards Unified Robustness Against Both Backdoor and Adversarial Attacks
by: Niu, Zhenxing, et al.
Published: (2024)

Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning
by: Ali, Hassan, et al.
Published: (2024)

SIFT-Graph: Benchmarking Multimodal Defense Against Image Adversarial Attacks With Robust Feature Graph
by: He, Jingjie, et al.
Published: (2025)

Let the Noise Speak: Harnessing Noise for a Unified Defense Against Adversarial and Backdoor Attacks
by: Shahriar, Md Hasan, et al.
Published: (2024)

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

Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning
by: Kabir, H M Dipu, et al.
Published: (2025)

Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoors
by: Kadir, Md Abdul, et al.
Published: (2024)

The Unseen Adversaries: Robust and Generalized Defense Against Adversarial Patches
by: Kumar, Vishesh, et al.
Published: (2026)

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

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

Backdoor Poisoning Attack Against Face Spoofing Attack Detection Methods
by: Iwamatsu, Shota, et al.
Published: (2025)

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

Robustness of Vision Language Models Against Split-Image Harmful Input Attacks
by: Rashid, Md Rafi Ur, et al.
Published: (2026)

TrojVLM: Backdoor Attack Against Vision Language Models
by: Lyu, Weimin, et al.
Published: (2024)

SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
by: Du, Lingyu, et al.
Published: (2025)

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

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

Robust and Transferable Backdoor Attacks Against Deep Image Compression With Selective Frequency Prior
by: Yu, Yi, et al.
Published: (2024)

Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks
by: Khanal, Aja, et al.
Published: (2025)

C-LEAD: Contrastive Learning for Enhanced Adversarial Defense
by: Ghosh, Suklav, et al.
Published: (2025)

PAD-FT: A Lightweight Defense for Backdoor Attacks via Data Purification and Fine-Tuning
by: Xu, Yukai, et al.
Published: (2024)

Adversarial Backdoor Defense in CLIP
by: Kuang, Junhao, et al.
Published: (2024)

Backdoor Cleaning without External Guidance in MLLM Fine-tuning
by: Rong, Xuankun, et al.
Published: (2025)

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

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

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

Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
by: Wang, Ruofei, et al.
Published: (2024)

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

Breaking the Limits of Quantization-Aware Defenses: QADT-R for Robustness Against Patch-Based Adversarial Attacks in QNNs
by: Guesmi, Amira, et al.
Published: (2025)

BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
by: Guo, Ji, et al.
Published: (2025)

DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
by: Zhou, Ziqi, et al.
Published: (2025)

LIDARLearn: A Unified Deep Learning Library for 3D Point Cloud Classification, Segmentation, and Self-Supervised Representation Learning
by: Ohamouddou, Said, et al.
Published: (2026)

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

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation
by: Abbasi, Bilal Hussain, et al.
Published: (2025)

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