Cover Image

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhou, Ziqi, Hu, Yifan, Song, Yufei, Li, Zijing, Hu, Shengshan, Zhang, Leo Yu, Yao, Dezhong, Zheng, Long, Jin, Hai
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

DarkSAM: Fooling Segment Anything Model to Segment Nothing
by: Zhou, Ziqi, et al.
Published: (2024)

Erosion Attack for Adversarial Training to Enhance Semantic Segmentation Robustness
by: Song, Yufei, et al.
Published: (2026)

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors
by: Zhou, Ziqi, et al.
Published: (2024)

PB-UAP: Hybrid Universal Adversarial Attack For Image Segmentation
by: Song, Yufei, et al.
Published: (2024)

DarkHash: A Data-Free Backdoor Attack Against Deep Hashing
by: Zhou, Ziqi, et al.
Published: (2025)

Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
by: Yan, Shihui, et al.
Published: (2026)

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples
by: Zhou, Ziqi, et al.
Published: (2024)

SegTrans: Transferable Adversarial Examples for Segmentation Models
by: Song, Yufei, et al.
Published: (2025)

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks
by: Xue, Lulu, et al.
Published: (2024)

Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks
by: Zhang, Xiaomei, et al.
Published: (2025)

ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents
by: Wang, Yichen, et al.
Published: (2025)

Transferable Adversarial Facial Images for Privacy Protection
by: Li, Minghui, et al.
Published: (2024)

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification
by: Wang, Xianlong, et al.
Published: (2024)

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization
by: Zhang, Yechao, et al.
Published: (2025)

UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
by: Xue, Lulu, et al.
Published: (2026)

Transferable Physical-World Adversarial Patches Against Object Detection in Autonomous Driving
by: Zhu, Zihui, et al.
Published: (2026)

Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability
by: Zhang, Yechao, et al.
Published: (2023)

Masked Language Model Based Textual Adversarial Example Detection
by: Zhang, Xiaomei, et al.
Published: (2023)

Detecting and Corrupting Convolution-based Unlearnable Examples
by: Li, Minghui, et al.
Published: (2023)

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning
by: Zhang, Hangtao, et al.
Published: (2023)

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

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature
by: Wang, Yichen, et al.
Published: (2024)

Timestep-Aware SVDQuant-GPTQ for W4A4 Quantization of Wan2.2-I2V
by: Wu, Junhao, et al.
Published: (2026)

SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
by: Han, Dongshen, et al.
Published: (2023)

Variational Bayes for Federated Continual Learning
by: Yao, Dezhong, et al.
Published: (2024)

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM
by: Yu, Lei, et al.
Published: (2025)

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need
by: Wang, Xianlong, et al.
Published: (2024)

Robot Collapse: Supply Chain Backdoor Attacks Against VLM-based Robotic Manipulation
by: Wang, Xianlong, et al.
Published: (2024)

DarkFed: A Data-Free Backdoor Attack in Federated Learning
by: Li, Minghui, et al.
Published: (2024)

Black-box Targeted Adversarial Attack on Segment Anything (SAM)
by: Zheng, Sheng, et al.
Published: (2023)

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation
by: Mi, Di, et al.
Published: (2024)

Detector Collapse: Physical-World Backdooring Object Detection to Catastrophic Overload or Blindness in Autonomous Driving
by: Zhang, Hangtao, et al.
Published: (2024)

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving
by: Zhang, Tianyuan, et al.
Published: (2024)

FedRKG: A Privacy-preserving Federated Recommendation Framework via Knowledge Graph Enhancement
by: Yao, Dezhong, et al.
Published: (2024)

Segmentation by registration-enabled SAM prompt engineering using five reference images
by: Chen, Yaxi, et al.
Published: (2024)

The Outline of Deception: Physical Adversarial Attacks on Traffic Signs Using Edge Patches
by: Ji, Haojie, et al.
Published: (2025)

MRPD: Undersampled MRI reconstruction by prompting a large latent diffusion model
by: Gao, Ziqi, et al.
Published: (2024)

Adversarial Attack Based Countermeasures against Deep Learning Side-Channel Attacks
by: Gu, Ruizhe, et al.
Published: (2020)

Dual-View Inference Attack: Machine Unlearning Amplifies Privacy Exposure
by: Xue, Lulu, et al.
Published: (2025)

MARS: A Malignity-Aware Backdoor Defense in Federated Learning
by: Wan, Wei, et al.
Published: (2025)