Copertina

Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Mitkiy, Alan, Smith, James, wong, Myungseo, Satou, Hana, Tanaka, Hiroshi, Johnson, Emily
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Mechanisms of Adversarial Data Augmentation for Robust and Adaptive Transfer Learning
di: Satou, Hana, et al.
Pubblicazione: (2025)

Disentangled Geometric Alignment with Adaptive Contrastive Perturbation for Reliable Domain Transfer
di: Collins, Emma, et al.
Pubblicazione: (2025)

Fusing Physics-Driven Strategies and Cross-Modal Adversarial Learning: Toward Multi-Domain Applications
di: Satou, Hana, et al.
Pubblicazione: (2024)

Geometrically Regularized Transfer Learning with On-Manifold and Off-Manifold Perturbation
di: Satou, Hana, et al.
Pubblicazione: (2025)

Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency
di: Tanaka, Hiroshi, et al.
Pubblicazione: (2025)

GAMA: Geometry-Aware Manifold Alignment via Structured Adversarial Perturbations for Robust Domain Adaptation
di: Satou, Hana, et al.
Pubblicazione: (2025)

Learning to Fuse: Modality-Aware Adaptive Scheduling for Robust Multimodal Foundation Models
di: Bennett, Liam, et al.
Pubblicazione: (2025)

A Training-Free Defense Framework for Robust Learned Image Compression
di: Song, Myungseo, et al.
Pubblicazione: (2024)

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

Improving Adversarial Training using Vulnerability-Aware Perturbation Budget
di: Fakorede, Olukorede, et al.
Pubblicazione: (2024)

Dynamic Perturbation-Adaptive Adversarial Training on Medical Image Classification
di: Li, Shuai, et al.
Pubblicazione: (2024)

Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation
di: Zhang, Lilin, et al.
Pubblicazione: (2026)

Theoretical Understanding of Learning from Adversarial Perturbations
di: Kumano, Soichiro, et al.
Pubblicazione: (2024)

Wide Two-Layer Networks can Learn from Adversarial Perturbations
di: Kumano, Soichiro, et al.
Pubblicazione: (2024)

DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling
di: Xie, Xin, et al.
Pubblicazione: (2024)

CAT: Contrastive Adversarial Training for Evaluating the Robustness of Protective Perturbations in Latent Diffusion Models
di: Peng, Sen, et al.
Pubblicazione: (2025)

Adversarial Training from Mean Field Perspective
di: Kumano, Soichiro, et al.
Pubblicazione: (2025)

APLA: Additional Perturbation for Latent Noise with Adversarial Training Enables Consistency
di: Yao, Yupu, et al.
Pubblicazione: (2023)

Epsilon: Exploring Comprehensive Visual-Semantic Projection for Multi-Label Zero-Shot Learning
di: Liu, Ziming, et al.
Pubblicazione: (2024)

Exploring the Camera Bias of Person Re-identification
di: Song, Myungseo, et al.
Pubblicazione: (2025)

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)

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

Dynamics-aware Adversarial Attack of Adaptive Neural Networks
di: Tao, An, et al.
Pubblicazione: (2022)

Adversarial Training with OCR Modality Perturbation for Scene-Text Visual Question Answering
di: Shen, Zhixuan, et al.
Pubblicazione: (2024)

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

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)

AdaGAT: Adaptive Guidance Adversarial Training for the Robustness of Deep Neural Networks
di: Liu, Zhenyu, et al.
Pubblicazione: (2025)

RoMA: Robust Malware Attribution via Byte-level Adversarial Training with Global Perturbations and Adversarial Consistency Regularization
di: Sun, Yuxia, et al.
Pubblicazione: (2025)

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning
di: Li, Geng, et al.
Pubblicazione: (2026)

Robust Fine-Tuning from Non-Robust Pretrained Models: Mitigating Suboptimal Transfer With Epsilon-Scheduling
di: Ngnawé, Jonas, et al.
Pubblicazione: (2025)

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

Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior
di: Lee, Chanhui, et al.
Pubblicazione: (2025)

Classification in Japanese Sign Language Based on Dynamic Facial Expressions
di: Tatsumi, Yui, et al.
Pubblicazione: (2024)

Adversarially Trained Object Detector for Unsupervised Domain Adaptation
di: Fujii, Kazuma, et al.
Pubblicazione: (2021)

Revisiting Adversarial Training under Hyperspectral Image
di: Zhang, Weihua, et al.
Pubblicazione: (2025)

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
di: Lin, Guang, et al.
Pubblicazione: (2024)

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

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