Cover Image

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models via Trigger Inversion and Activation Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sun, Mengyuan, Li, Yu, Liu, Yuchen, Du, Bo, Ge, Yunjie
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

CLIP-Inspector: Model-Level Backdoor Detection for Prompt-Tuned CLIP via OOD Trigger Inversion
by: Jindal, Akshit, et al.
Published: (2026)

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

Robust Anti-Backdoor Instruction Tuning in LVLMs
by: Xun, Yuan, 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)

REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
by: Chen, Yukun, 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)

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

Backdoor Contrastive Learning via Bi-level Trigger Optimization
by: Sun, Weiyu, et al.
Published: (2024)

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

Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
by: Wang, Ruotong, et al.
Published: (2023)

Backdoor Attack with Sparse and Invisible Trigger
by: Gao, Yinghua, et al.
Published: (2023)

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation
by: Yu, Yi, et al.
Published: (2025)

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

BadBlocks: Low-Cost and Stealthy Backdoor Attacks Tailored for Text-to-Image Diffusion Models
by: Wu, Jia, et al.
Published: (2025)

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

Differentially Private Fine-Tuning of Diffusion Models
by: Tsai, Yu-Lin, et al.
Published: (2024)

An Inversion-based Measure of Memorization for Diffusion Models
by: Ma, Zhe, et al.
Published: (2024)

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

Identifying Physically Realizable Triggers for Backdoored Face Recognition Networks
by: Raj, Ankita, et al.
Published: (2025)

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

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

Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable
by: Liu, Haozhe, et al.
Published: (2024)

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

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

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

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

Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning
by: Sami, Hasin Us, et al.
Published: (2025)

Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP
by: Singh, Naman Deep, et al.
Published: (2024)

Robust Backdoor Removal by Reconstructing Trigger-Activated Changes in Latent Representation
by: Iwahana, Kazuki, et al.
Published: (2025)

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

SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization
by: Rong, Xuankun, et al.
Published: (2025)

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

Proactive Adversarial Defense: Harnessing Prompt Tuning in Vision-Language Models to Detect Unseen Backdoored Images
by: Stein, Kyle, et al.
Published: (2024)

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

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

MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense
by: Qiu, Yixiang, et al.
Published: (2024)

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

Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
by: Zhu, Mingyan, et al.
Published: (2023)