Imagen de Portada

Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Wu, Jialin, Pan, Kaikai, Chen, Yanjiao, Deng, Jiangyi, Pang, Shengyuan, Xu, Wenyuan
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
por: Li, Xinfeng, et al.
Publicado: (2025)

Improving the Transferability of Adversarial Examples by Inverse Knowledge Distillation
por: Wu, Wenyuan, et al.
Publicado: (2025)

SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
por: Li, Xinfeng, et al.
Publicado: (2024)

Protego: User-Centric Pose-Invariant Privacy Protection Against Face Recognition-Induced Digital Footprint Exposure
por: Wang, Ziling, et al.
Publicado: (2025)

Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations
por: Zhang, Haimin, et al.
Publicado: (2021)

Adversarial Examples Detection with Bayesian Neural Network
por: Li, Yao, et al.
Publicado: (2021)

Vision Transformer-based Adversarial Domain Adaptation
por: Li, Yahan, et al.
Publicado: (2024)

Adversarial Example Defense via Perturbation Grading Strategy
por: Zhu, Shaowei, et al.
Publicado: (2022)

GradID: Adversarial Detection via Intrinsic Dimensionality of Gradients
por: Razmjoo, Mohammad Mahdi, et al.
Publicado: (2025)

Adversarial Examples Are Not Real Features
por: Li, Ang, et al.
Publicado: (2023)

AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptation
por: Peng, Heqi, et al.
Publicado: (2024)

Improving Transferability of Adversarial Examples via Bayesian Attacks
por: Li, Qizhang, et al.
Publicado: (2023)

ViTGuard: Attention-aware Detection against Adversarial Examples for Vision Transformer
por: Sun, Shihua, et al.
Publicado: (2024)

Boosting Imperceptibility of Stable Diffusion-based Adversarial Examples Generation with Momentum
por: Haque, Nashrah, et al.
Publicado: (2024)

SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models
por: Deng, Jiangyi, et al.
Publicado: (2024)

Enhancing Adversarial Example Detection Through Model Explanation
por: Ma, Qian, et al.
Publicado: (2025)

Transferable Adversarial Examples with Bayes Approach
por: Fan, Mingyuan, et al.
Publicado: (2022)

Do Counterfactual Examples Complicate Adversarial Training?
por: Yeats, Eric, et al.
Publicado: (2024)

PatchGuard: Adversarially Robust Anomaly Detection and Localization through Vision Transformers and Pseudo Anomalies
por: Nafez, Mojtaba, et al.
Publicado: (2025)

SemDiff: Generating Natural Unrestricted Adversarial Examples via Semantic Attributes Optimization in Diffusion Models
por: Dai, Zeyu, et al.
Publicado: (2025)

Evaluating the Adversarial Robustness of Detection Transformers
por: Nazeri, Amirhossein, et al.
Publicado: (2024)

Legilimens: Practical and Unified Content Moderation for Large Language Model Services
por: Wu, Jialin, et al.
Publicado: (2024)

SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis
por: Tian, Huiyuan, et al.
Publicado: (2024)

Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
por: Guo, Qi, et al.
Publicado: (2024)

Multi-Tailed Vision Transformer for Efficient Inference
por: Wang, Yunke, et al.
Publicado: (2022)

Adversarial Examples in the Physical World: A Survey
por: Wang, Jiakai, et al.
Publicado: (2023)

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
por: Gui, Jie, et al.
Publicado: (2024)

Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters
por: Warnecke, Alexander, et al.
Publicado: (2026)

Uncertainty Meets Diversity: A Comprehensive Active Learning Framework for Indoor 3D Object Detection
por: Wang, Jiangyi, et al.
Publicado: (2025)

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium
por: Xiao, Qingxin, et al.
Publicado: (2026)

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

Analyzing Physical Adversarial Example Threats to Machine Learning in Election Systems
por: Kamal, Khaleque Md Aashiq, et al.
Publicado: (2026)

AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Models
por: Dai, Xuelong, et al.
Publicado: (2023)

Going Further: Flatness at the Rescue of Early Stopping for Adversarial Example Transferability
por: Gubri, Martin, et al.
Publicado: (2023)

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
por: Liu, Yixin, et al.
Publicado: (2023)

Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics
por: Li, Shuai, et al.
Publicado: (2024)

PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
por: Zhang, Yudong, et al.
Publicado: (2024)

DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples
por: Nafi, Abdullah Al Nomaan, et al.
Publicado: (2025)

Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
por: Xu, Qi, et al.
Publicado: (2025)

Exploring Aleatoric Uncertainty in Object Detection via Vision Foundation Models
por: Cui, Peng, et al.
Publicado: (2024)