Cover Image

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Kuanrong, Liang, Siyuan, Liang, Jiawei, Dai, Pengwen, Cao, Xiaochun
Format:	Preprint
Published:	2024
Subjects:	Cryptography and Security Artificial Intelligence 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

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

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

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

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

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

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism
by: Chen, Beitao, et al.
Published: (2025)

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
by: Lin, Weilin, et al.
Published: (2024)

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

SSL-OTA: Unveiling Backdoor Threats in Self-Supervised Learning for Object Detection
by: Wang, Qiannan, et al.
Published: (2023)

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

OmniSafeBench-MM: A Unified Benchmark and Toolbox for Multimodal Jailbreak Attack-Defense Evaluation
by: Jia, Xiaojun, et al.
Published: (2025)

Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
by: Zhang, Yimeng, et al.
Published: (2024)

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

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

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

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

PASTA: A Patch-Agnostic Twofold-Stealthy Backdoor Attack on Vision Transformers
by: Liu, Dazhuang, et al.
Published: (2026)

Towards Physical World Backdoor Attacks against Skeleton Action Recognition
by: Zheng, Qichen, et al.
Published: (2024)

Video Inpainting Localization with Contrastive Learning
by: Lou, Zijie, et al.
Published: (2024)

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

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

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning
by: Cheng, Siyuan, et al.
Published: (2024)

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

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

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

Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Models
by: Lai, Songning, et al.
Published: (2024)

Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design
by: Sun, Yuhao, et al.
Published: (2025)

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

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
by: Li, Ziqiang, et al.
Published: (2023)

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

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection
by: Liang, Ziyou, et al.
Published: (2024)

Unsupervised Backdoor Detection and Mitigation for Spiking Neural Networks
by: Li, Jiachen, et al.
Published: (2025)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
by: Xue, Lulu, et al.
Published: (2026)

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

Token-Level Constraint Boundary Search for Jailbreaking Text-to-Image Models
by: Liu, Jiangtao, et al.
Published: (2025)

Scaling Exposes the Trigger: Input-Level Backdoor Detection in Text-to-Image Diffusion Models via Cross-Attention Scaling
by: Li, Zida, et al.
Published: (2026)

IPBA: Imperceptible Perturbation Backdoor Attack in Federated Self-Supervised Learning
by: Wang, Jiayao, et al.
Published: (2025)

IMU: Influence-guided Machine Unlearning
by: Fan, Xindi, et al.
Published: (2025)

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

Backdoor Directions in Vision Transformers
by: Karayalcin, Sengim, et al.
Published: (2026)