Buchumschlag

Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Ren, Yuchen, Zhao, Zhengyu, Lin, Chenhao, Yang, Bo, Zhou, Lu, Liu, Zhe, Shen, Chao
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Computer Vision and Pattern Recognition Cryptography and Security
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
von: Ren, Yuchen, et al.
Veröffentlicht: (2024)

Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
von: Zheng, Junhao, et al.
Veröffentlicht: (2024)

Quantization Aware Attack: Enhancing Transferable Adversarial Attacks by Model Quantization
von: Yang, Yulong, et al.
Veröffentlicht: (2023)

Privacy on the Fly: A Predictive Adversarial Transformation Network for Mobile Sensor Data
von: Song, Tianle, et al.
Veröffentlicht: (2025)

A Survey on Adversarial Machine Learning for Code Data: Realistic Threats, Countermeasures, and Interpretations
von: Yang, Yulong, et al.
Veröffentlicht: (2024)

Revisiting Adversarial Patch Defenses on Object Detectors: Unified Evaluation, Large-Scale Dataset, and New Insights
von: Zheng, Junhao, et al.
Veröffentlicht: (2025)

Prediction Inconsistency Helps Achieve Generalizable Detection of Adversarial Examples
von: Han, Sicong, et al.
Veröffentlicht: (2025)

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
von: Cao, Hanwen, et al.
Veröffentlicht: (2025)

TwoHamsters: Benchmarking Multi-Concept Compositional Unsafety in Text-to-Image Models
von: Zhang, Chaoshuo, et al.
Veröffentlicht: (2026)

Revisiting Transferable Adversarial Images: Systemization, Evaluation, and New Insights
von: Zhao, Zhengyu, et al.
Veröffentlicht: (2023)

Generalizable Targeted Data Poisoning against Varying Physical Objects
von: Chen, Zhizhen, et al.
Veröffentlicht: (2024)

Systematic Categorization, Construction and Evaluation of New Attacks against Multi-modal Mobile GUI Agents
von: Yang, Yulong, et al.
Veröffentlicht: (2024)

Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
von: Zhang, Chiyu, et al.
Veröffentlicht: (2024)

Boosting Generative Adversarial Transferability with Self-supervised Vision Transformer Features
von: Wu, Shangbo, et al.
Veröffentlicht: (2025)

Boosting Adversarial Transferability with Spatial Adversarial Alignment
von: Chen, Zhaoyu, et al.
Veröffentlicht: (2025)

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

Revisiting Training-Inference Trigger Intensity in Backdoor Attacks
von: Lin, Chenhao, et al.
Veröffentlicht: (2025)

Improving Adversarial Transferability with Neighbourhood Gradient Information
von: Guo, Haijing, et al.
Veröffentlicht: (2024)

Improving Adversarial Transferability of Vision-Language Pre-training Models through Collaborative Multimodal Interaction
von: Fu, Jiyuan, et al.
Veröffentlicht: (2024)

SlowPerception: Physical-World Latency Attack against Visual Perception in Autonomous Driving
von: Ma, Chen, et al.
Veröffentlicht: (2024)

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

LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection
von: Tian, Jiwei, et al.
Veröffentlicht: (2024)

Attacking Transformers with Feature Diversity Adversarial Perturbation
von: Gao, Chenxing, et al.
Veröffentlicht: (2024)

Improving Adversarial Robustness via Feature Pattern Consistency Constraint
von: Hu, Jiacong, et al.
Veröffentlicht: (2024)

Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
von: Liu, Yugeng, et al.
Veröffentlicht: (2023)

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

Boosting Adversarial Transferability via Residual Perturbation Attack
von: Peng, Jinjia, et al.
Veröffentlicht: (2025)

Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation
von: Du, Xia, et al.
Veröffentlicht: (2025)

Port Forwarding Services Are Forwarding Security Risks
von: Wang, Haoyuan, et al.
Veröffentlicht: (2024)

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models
von: Zhang, Rui, et al.
Veröffentlicht: (2025)

Few-Shot Adversarial Prompt Learning on Vision-Language Models
von: Zhou, Yiwei, et al.
Veröffentlicht: (2024)

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
von: Wang, Jiafeng, et al.
Veröffentlicht: (2022)

One Prompt to Verify Your Models: Black-Box Text-to-Image Models Verification via Non-Transferable Adversarial Attacks
von: Guo, Ji, et al.
Veröffentlicht: (2024)

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt
von: Ying, Zonghao, et al.
Veröffentlicht: (2024)

Enhancing Adversarial Transferability with Adversarial Weight Tuning
von: Chen, Jiahao, et al.
Veröffentlicht: (2024)

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

When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm
von: Leng, Ye, et al.
Veröffentlicht: (2026)

Improving Adversarial Robustness in Android Malware Detection by Reducing the Impact of Spurious Correlations
von: Bostani, Hamid, et al.
Veröffentlicht: (2024)

Transferable Adversarial Attacks on SAM and Its Downstream Models
von: Xia, Song, et al.
Veröffentlicht: (2024)

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