Copertina

Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Chanhui, Song, Yeonghwan, Son, Jeany
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Universal Image Immunization against Diffusion-based Image Editing via Semantic Injection
di: Lee, Chanhui, et al.
Pubblicazione: (2026)

Pseudo-RIS: Distinctive Pseudo-supervision Generation for Referring Image Segmentation
di: Yu, Seonghoon, et al.
Pubblicazione: (2024)

Latent Expression Generation for Referring Image Segmentation and Grounding
di: Yu, Seonghoon, et al.
Pubblicazione: (2025)

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
di: Yu, Seonghoon, et al.
Pubblicazione: (2026)

Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity
di: Yu, Seonghoon, et al.
Pubblicazione: (2025)

Adversarial Pseudo-replay for Exemplar-free Class-incremental Learning
di: Honda, Hiroto
Pubblicazione: (2025)

Texture Re-scalable Universal Adversarial Perturbation
di: Huang, Yihao, et al.
Pubblicazione: (2024)

Online Generic Event Boundary Detection
di: Jung, Hyungrok, et al.
Pubblicazione: (2025)

Stabilizing Adversarially Learned One-Class Novelty Detection Using Pseudo Anomalies
di: Zaheer, Muhammad Zaigham, et al.
Pubblicazione: (2022)

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

A Simple Baseline with Single-encoder for Referring Image Segmentation
di: Yu, Seonghoon, et al.
Pubblicazione: (2024)

Adaptive Perturbation for Adversarial Attack
di: Yuan, Zheng, et al.
Pubblicazione: (2021)

AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields
di: Kim, Woo Jae, et al.
Pubblicazione: (2025)

Detecting Adversarial Data using Perturbation Forgery
di: Wang, Qian, et al.
Pubblicazione: (2024)

Adversarial Universal Stickers: Universal Perturbation Attacks on Traffic Sign using Stickers
di: Etim, Anthony, et al.
Pubblicazione: (2025)

LAMP: Learning Universal Adversarial Perturbations for Multi-Image Tasks via Pre-trained Models
di: Ishmam, Alvi Md, et al.
Pubblicazione: (2026)

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations
di: Wang, Chao, et al.
Pubblicazione: (2023)

A Mimetic Detector for Adversarial Image Perturbations
di: Corbino, Johnny
Pubblicazione: (2026)

Relation-Guided Adversarial Learning for Data-free Knowledge Transfer
di: Liang, Yingping, et al.
Pubblicazione: (2024)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
di: Fang, Hao, et al.
Pubblicazione: (2024)

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
di: Wan, Cong, et al.
Pubblicazione: (2024)

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

Adversarial Attention Perturbations for Large Object Detection Transformers
di: Yahn, Zachary, et al.
Pubblicazione: (2025)

Improving Weakly-Supervised Object Localization Using Adversarial Erasing and Pseudo Label
di: Kang, Byeongkeun, et al.
Pubblicazione: (2024)

Visual-Friendly Concept Protection via Selective Adversarial Perturbations
di: Mi, Xiaoyue, et al.
Pubblicazione: (2024)

Practical No-box Adversarial Attacks with Training-free Hybrid Image Transformation
di: Zhang, Qilong, et al.
Pubblicazione: (2022)

One Noise to Rule Them All: Multi-View Adversarial Attacks with Universal Perturbation
di: Ergezer, Mehmet, et al.
Pubblicazione: (2024)

Energy-Based Pseudo-Label Refining for Source-free Domain Adaptation
di: Meng, Xinru, et al.
Pubblicazione: (2025)

Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval
di: Jiang, Yiyang, et al.
Pubblicazione: (2024)

On the Reliability of Vision-Language Models Under Adversarial Frequency-Domain Perturbations
di: Vice, Jordan, et al.
Pubblicazione: (2025)

Sample-agnostic Adversarial Perturbation for Vision-Language Pre-training Models
di: Zheng, Haonan, et al.
Pubblicazione: (2024)

Adversarial Attacks on Robot Localization Systems via Deep Feature Perturbation
di: Li, Zhenyu, et al.
Pubblicazione: (2026)

Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?
di: Fu, Yonggan, et al.
Pubblicazione: (2022)

APPLE: Adversarial Privacy-aware Perturbations on Latent Embedding for Unfairness Mitigation
di: Xu, Zikang, et al.
Pubblicazione: (2024)

Consistent Attack: Universal Adversarial Perturbation on Embodied Vision Navigation
di: Ying, Chengyang, et al.
Pubblicazione: (2022)

Doubly-Universal Adversarial Perturbations: Deceiving Vision-Language Models Across Both Images and Text with a Single Perturbation
di: Kim, Hee-Seon, et al.
Pubblicazione: (2024)

VVLoc: Prior-free 3-DoF Vehicle Visual Localization
di: Huang, Ze, et al.
Pubblicazione: (2026)

InFusionSurf: Refining Neural RGB-D Surface Reconstruction Using Per-Frame Intrinsic Refinement and TSDF Fusion Prior Learning
di: Lee, Seunghwan, et al.
Pubblicazione: (2023)

Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
di: Ma, Lina, et al.
Pubblicazione: (2025)

NAPPure: Adversarial Purification for Robust Image Classification under Non-Additive Perturbations
di: Nan, Junjie, et al.
Pubblicazione: (2025)