Image de couverture de livre

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Fang, Hao, Kong, Jiawei, Yu, Wenbo, Chen, Bin, Li, Jiawei, Wu, Hao, Xia, Shutao, Xu, Ke
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Cryptography and Security
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

DUAP: Dual-task Universal Adversarial Perturbations Against Voice Control Systems
par: Sun, Suyang, et autres
Publié: (2026)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
par: Ying, Chengyang, et autres
Publié: (2022)

Joint Universal Adversarial Perturbations with Interpretations
par: Ning, Liang-bo, et autres
Publié: (2024)

UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
par: Sun, Ye, et autres
Publié: (2024)

Protecting Copyright of Medical Pre-trained Language Models: Training-Free Backdoor Model Watermarking
par: Kong, Cong, et autres
Publié: (2024)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
par: Wang, Youze, et autres
Publié: (2025)

Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language Models
par: Peng, Zuquan, et autres
Publié: (2025)

Adversarial Text Generation with Dynamic Contextual Perturbation
par: Waghela, Hetvi, et autres
Publié: (2025)

Adversarial Perturbations Cannot Reliably Protect Artists From Generative AI
par: Hönig, Robert, et autres
Publié: (2024)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
par: Kim, Hee-Seon, et autres
Publié: (2024)

Erasing Radio Frequency Fingerprints via Active Adversarial Perturbation
par: Lu, Zhaoyi, et autres
Publié: (2024)

"What is the Problem Space?" Defining Host-space Adversarial Perturbations against Network Intrusion Detection Systems
par: Verkerken, Miel, et autres
Publié: (2026)

A Cross-Modal Prompt Injection Attack against Large Vision-Language Models with Image-Only Perturbation
par: Yang, Hao, et autres
Publié: (2026)

A Novel and Practical Universal Adversarial Perturbations against Deep Reinforcement Learning based Intrusion Detection Systems
par: Zhang, H., et autres
Publié: (2025)

Diffusion-Guided Adversarial Perturbation Injection for Generalizable Defense Against Facial Manipulations
par: Li, Yue, et autres
Publié: (2026)

Low Rank Adaptation for Adversarial Perturbation
par: Liu, Han, et autres
Publié: (2026)

DMLDroid: Deep Multimodal Fusion Framework for Android Malware Detection with Resilience to Code Obfuscation and Adversarial Perturbations
par: Trung, Doan Minh, et autres
Publié: (2025)

Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
par: Fang, Junyuan, et autres
Publié: (2025)

Cross-Input Certified Training for Universal Perturbations
par: Xu, Changming, et autres
Publié: (2024)

Attacking Transformers with Feature Diversity Adversarial Perturbation
par: Gao, Chenxing, et autres
Publié: (2024)

CR-UTP: Certified Robustness against Universal Text Perturbations on Large Language Models
par: Lou, Qian, et autres
Publié: (2024)

RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations for Universal Robustness
par: Jiang, Enyi, et autres
Publié: (2024)

Less Is More: Sparse and Cooperative Perturbation for Point Cloud Attacks
par: Tang, Keke, et autres
Publié: (2025)

AGNNCert: Defending Graph Neural Networks against Arbitrary Perturbations with Deterministic Certification
par: Li, Jiate, et autres
Publié: (2025)

Provably Robust Explainable Graph Neural Networks against Graph Perturbation Attacks
par: Li, Jiate, et autres
Publié: (2025)

EveGuard: Defeating Vibration-based Side-Channel Eavesdropping with Audio Adversarial Perturbations
par: Chang, Jung-Woo, et autres
Publié: (2024)

Adversarial Universal Stickers: Universal Perturbation Attacks on Traffic Sign using Stickers
par: Etim, Anthony, et autres
Publié: (2025)

Evaluating the Vulnerability of ML-Based Ethereum Phishing Detectors to Single-Feature Adversarial Perturbations
par: Alghuried, Ahod, et autres
Publié: (2025)

Towards Imperceptible Adversarial Attacks for Time Series Classification with Local Perturbations and Frequency Analysis
par: Gu, Wenwei, et autres
Publié: (2025)

Stealthy Targeted Backdoor Attacks against Image Captioning
par: Fan, Wenshu, et autres
Publié: (2024)

FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
par: Yan, Xinhai, et autres
Publié: (2025)

When Fine-Tuning is Not Enough: Lessons from HSAD on Hybrid and Adversarial Audio Spoof Detection
par: Hu, Bin, et autres
Publié: (2025)

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation
par: Chang, Shuyu, et autres
Publié: (2026)

Explainability-Based Adversarial Attack on Graphs Through Edge Perturbation
par: Chanda, Dibaloke, et autres
Publié: (2023)

Bitstream Collisions in Neural Image Compression via Adversarial Perturbations
par: Madden, Jordan, et autres
Publié: (2025)

Adversarial attacks against Modern Vision-Language Models
par: La Torre, Alejandro Paredes
Publié: (2026)

LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
par: Gong, Yuyang, et autres
Publié: (2026)

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models
par: Yin, Ziyi, et autres
Publié: (2023)

PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
par: Mangaokar, Neal, et autres
Publié: (2024)

Modeling the Attack: Detecting AI-Generated Text by Quantifying Adversarial Perturbations
par: Teja, Lekkala Sai, et autres
Publié: (2025)