Cover Image

Theoretical Analysis of Relative Errors in Gradient Computations for Adversarial Attacks with CE Loss

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yu, Yunrui, Su, Hang, Xu, Cheng-zhong, Su, Zhizhong, Zhu, Jun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RCR-AF: Enhancing Model Generalization via Rademacher Complexity Reduction Activation Function
by: Yu, Yunrui, et al.
Published: (2025)

Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification
by: Chen, Jun, et al.
Published: (2025)

Adversarial Attacks on Medical Hyperspectral Imaging Exploiting Spectral-Spatial Dependencies and Multiscale Features
by: Gu, Yunrui, et al.
Published: (2026)

AEMIM: Adversarial Examples Meet Masked Image Modeling
by: Xiang, Wenzhao, et al.
Published: (2024)

Human-Imperceptible Physical Adversarial Attack for NIR Face Recognition Models
by: Xie, Songyan, et al.
Published: (2025)

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
by: Wu, Lingxuan, et al.
Published: (2024)

Emotion Loss Attacking: Adversarial Attack Perception for Skeleton based on Multi-dimensional Features
by: Liu, Feng, et al.
Published: (2024)

Reinforced Embodied Active Defense: Exploiting Adaptive Interaction for Robust Visual Perception in Adversarial 3D Environments
by: Yang, Xiao, et al.
Published: (2025)

Adversarial Evasion Attacks on Computer Vision using SHAP Values
by: Mollard, Frank, et al.
Published: (2026)

ALA: Naturalness-aware Adversarial Lightness Attack
by: Huang, Yihao, et al.
Published: (2022)

DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks
by: Kang, Caixin, et al.
Published: (2023)

Why the Maximum Second Derivative of Activations Matters for Adversarial Robustness
by: Yu, Yunrui, et al.
Published: (2026)

Adversarial Error Correction for Visual Autoregressive Generation
by: Bi, Ligong, et al.
Published: (2026)

A Comprehensive Survey of Continual Learning: Theory, Method and Application
by: Wang, Liyuan, et al.
Published: (2023)

Real-world Adversarial Defense against Patch Attacks based on Diffusion Model
by: Wei, Xingxing, et al.
Published: (2024)

Differential Privacy Image Generation with Reconstruction Loss and Noise Injection Using an Error Feedback SGD
by: Ma, Qiwei, et al.
Published: (2026)

Downstream Transfer Attack: Adversarial Attacks on Downstream Models with Pre-trained Vision Transformers
by: Zheng, Weijie, et al.
Published: (2024)

Adversarial Flow Matching for Imperceptible Attacks on End-to-End Autonomous Driving
by: Zeng, Xinyu, et al.
Published: (2026)

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models
by: Liu, Han, et al.
Published: (2026)

Adversarial Attack for RGB-Event based Visual Object Tracking
by: Chen, Qiang, et al.
Published: (2025)

Steal Now and Attack Later: Evaluating Robustness of Object Detection against Black-box Adversarial Attacks
by: Chen, Erh-Chung, et al.
Published: (2024)

Adversarial Attack Against Images Classification based on Generative Adversarial Networks
by: Yang, Yahe
Published: (2024)

Instance-Level Trojan Attacks on Visual Question Answering via Adversarial Learning in Neuron Activation Space
by: Sun, Yuwei, et al.
Published: (2023)

Defending From Physically-Realizable Adversarial Attacks Through Internal Over-Activation Analysis
by: Rossolini, Giulio, et al.
Published: (2022)

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

GI-NAS: Boosting Gradient Inversion Attacks Through Adaptive Neural Architecture Search
by: Yu, Wenbo, et al.
Published: (2024)

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models
by: Li, Jiayu, et al.
Published: (2025)

Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning
by: Fang, Qingqing, et al.
Published: (2024)

BIP3D: Bridging 2D Images and 3D Perception for Embodied Intelligence
by: Lin, Xuewu, et al.
Published: (2024)

Generalizable Object Re-Identification via Visual In-Context Prompting
by: Huang, Zhizhong, et al.
Published: (2025)

AdvDINO: Domain-Adversarial Self-Supervised Representation Learning for Spatial Proteomics
by: Su, Stella, et al.
Published: (2025)

Cheating Stereo Matching in Full-scale: Physical Adversarial Attack against Binocular Depth Estimation in Autonomous Driving
by: Zhao, Kangqiao, et al.
Published: (2025)

Convolution-based Probability Gradient Loss for Semantic Segmentation
by: Shan, Guohang, et al.
Published: (2024)

Rethinking Model Ensemble in Transfer-based Adversarial Attacks
by: Chen, Huanran, et al.
Published: (2023)

Concept-based Adversarial Attack: a Probabilistic Perspective
by: Zhang, Andi, et al.
Published: (2025)

Transferable Adversarial Face Attack with Text Controlled Attribute
by: Li, Wenyun, et al.
Published: (2024)

Multimodal Sentiment Analysis based on Multi-channel and Symmetric Mutual Promotion Feature Fusion
by: Zhu, Wangyuan, et al.
Published: (2026)

GRILL: Restoring Gradient Signal in Ill-Conditioned Layers for More Effective Adversarial Attacks on Autoencoders
by: Ramanaik, Chethan Krishnamurthy, et al.
Published: (2025)

Exploring the Transferability of Visual Prompting for Multimodal Large Language Models
by: Zhang, Yichi, et al.
Published: (2024)

Visual Generation Without Guidance
by: Chen, Huayu, et al.
Published: (2025)