Cover Image

Assimilation Matters: Model-level Backdoor Detection in Vision-Language Pretrained Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhongqi, Zhang, Jie, Shan, Shiguang, Chen, Xilin
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
by: Wang, Zhongqi, et al.
Published: (2025)

EntropyScan: Towards Model-level Backdoor Detection in LVLMs via Visual Attention Entropy
by: Ge, Xuanyu, et al.
Published: (2026)

T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
by: Wang, Zhongqi, et al.
Published: (2024)

Trigger without Trace: Towards Stealthy Backdoor Attack on Text-to-Image Diffusion Models
by: Zhang, Jie, et al.
Published: (2025)

What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Models
by: Nie, Sen, et al.
Published: (2026)

FullLoRA: Efficiently Boosting the Robustness of Pretrained Vision Transformers
by: Yuan, Zheng, et al.
Published: (2024)

VOPE: Revisiting Hallucination of Vision-Language Models in Voluntary Imagination Task
by: Long, Xingming, et al.
Published: (2025)

REVAL: A Comprehension Evaluation on Reliability and Values of Large Vision-Language Models
by: Zhang, Jie, et al.
Published: (2025)

Measuring the Measurers: Quality Evaluation of Hallucination Benchmarks for Large Vision-Language Models
by: Yan, Bei, et al.
Published: (2024)

MM-MoralBench: A MultiModal Moral Evaluation Benchmark for Large Vision-Language Models
by: Yan, Bei, et al.
Published: (2024)

Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
by: Long, Xingming, et al.
Published: (2024)

Semantic or Covariate? A Study on the Intractable Case of Out-of-Distribution Detection
by: Long, Xingming, et al.
Published: (2024)

UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
by: Liang, Jiachen, et al.
Published: (2024)

Dysca: A Dynamic and Scalable Benchmark for Evaluating Perception Ability of LVLMs
by: Zhang, Jie, et al.
Published: (2024)

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
by: Wang, Sibo, et al.
Published: (2024)

Steering Vision-Language Pre-trained Models for Incremental Face Presentation Attack Detection
by: Li, Haoze, et al.
Published: (2025)

T2VAttack: Adversarial Attack on Text-to-Video Diffusion Models
by: Li, Changzhen, et al.
Published: (2025)

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
by: Nie, Sen, et al.
Published: (2026)

Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement
by: Yuan, Zheng, et al.
Published: (2024)

V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs
by: Nie, Sen, et al.
Published: (2025)

ACT Now: Preempting LVLM Hallucinations via Adaptive Context Integration
by: Yan, Bei, et al.
Published: (2026)

Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating
by: Cao, Xiangkui, et al.
Published: (2026)

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
by: Wang, Tianyue, et al.
Published: (2025)

Component-Based Out-of-Distribution Detection
by: Liu, Wenrui, et al.
Published: (2026)

EfficientMT: Efficient Temporal Adaptation for Motion Transfer in Text-to-Video Diffusion Models
by: Cai, Yufei, et al.
Published: (2025)

DIVE: Inverting Conditional Diffusion Models for Discriminative Tasks
by: Li, Yinqi, et al.
Published: (2025)

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

CtrLoRA: An Extensible and Efficient Framework for Controllable Image Generation
by: Xu, Yifeng, et al.
Published: (2024)

Dual Attention Guided Defense Against Malicious Edits
by: Zhang, Jie, et al.
Published: (2025)

Towards Transferable Defense Against Malicious Image Edits
by: Zhang, Jie, et al.
Published: (2025)

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
by: Yang, Junqi, et al.
Published: (2026)

Generalized Face Liveness Detection via De-fake Face Generator
by: Long, Xingming, et al.
Published: (2024)

EgoMotion: Hierarchical Reasoning and Diffusion for Egocentric Vision-Language Motion Generation
by: Hou, Ruibing, et al.
Published: (2026)

Revisiting Logit Distributions for Reliable Out-of-Distribution Detection
by: Liang, Jiachen, et al.
Published: (2025)

Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness
by: Wang, Sibo, et al.
Published: (2024)

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

BIMM: Brain Inspired Masked Modeling for Video Representation Learning
by: Wan, Zhifan, et al.
Published: (2024)

Task-adaptive Q-Face
by: Sun, Haomiao, et al.
Published: (2024)

Revisiting Prompt Pretraining of Vision-Language Models
by: Chen, Zhenyuan, et al.
Published: (2024)

Jodi: Unification of Visual Generation and Understanding via Joint Modeling
by: Xu, Yifeng, et al.
Published: (2025)