Adversarial Color

Adversarial color research explores how subtle manipulations of image color can deceive deep learning models, primarily focusing on improving the robustness of these models and protecting against unauthorized use of images. Current research investigates methods to generate these adversarial color perturbations, often targeting specific frequency components of images or leveraging self-supervised learning techniques to create more robust models. This field is significant because it addresses vulnerabilities in computer vision systems, impacting areas like image authentication, artistic protection, and the security of facial recognition technology.

Papers

November 26, 2024

Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum
Jing-Yang Wei, Hao Huang, Xin Zhang, De-Mao Ye, Yi Li, Le Wang, Yao-Guang Ma, Yang-Hui Li
Imaging Technique Neuromorphic Event Ultra High Resolution Dual Discriminator Cycle GAN Adversarial Color Infrared Imaging

June 9, 2024

ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations
Sravanti Addepalli, Priyam Dey, R. Venkatesh Babu
Self Supervised Learning Adversarial Training Robust Representation Adversarial Color

January 18, 2024

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack
Zhongliang Guo, Junhao Dong, Yifei Qian, Kaixuan Wang, Weiye Li, Ziheng Guo, Yuheng Wang, Yanli Li, Ognjen Arandjelović, Lei Fang
Neural Style Transfer Image Protection Adaptive Adversarial Attack Adversarial Color

October 31, 2023

LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations
Kunyu Wang, Juluan Shi, Wenxuan Wang
Adversarial Attack Adversarial Example Adversarial Perturbation High Frequency Adversarial Color Natural Adversarial

July 16, 2023

On the Robustness of Split Learning against Adversarial Attacks
Mingyuan Fan, Cen Chen, Chengyu Wang, Wenmeng Zhou, Jun Huang
Adversarial Attack Native Robustness Adversarial Example Split Learning Collaborative Deep Learning Adversarial Color

March 25, 2023

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation
Xu Zheng, Jinjing Zhu, Yexin Liu, Zidong Cao, Chong Fu, Lin Wang
Unsupervised Domain Adaptation Style Consistency Distortion Aware Equirectangular Projection Panoramic Semantic Segmentation Adversarial Color Projection Fusion

September 19, 2022

Adversarial Color Projection: A Projector-based Physical Attack to DNNs
Chengyin Hu, Weiwen Shi, Ling Tian
Deep Neural Network Adversarial Attack Based Physical Attack Physical Attack Adversarial Color

September 2, 2022

Adversarial Color Film: Effective Physical-World Attack to DNNs
Chengyin Hu, Weiwen Shi
Deep Neural Network Adversarial Training Physical World Attack Based Physical Attack Adversarial Color

June 19, 2022

Low-Mid Adversarial Perturbation against Unauthorized Face Recognition System
Jiaming Zhang, Qi Yi, Dongyuan Lu, Jitao Sang
Adversarial Training Adversarial Perturbation Adversarial Color Unauthorized Facial Recognition

Adversarial Color

Papers

Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum

ProFeAT: Projected Feature Adversarial Training for Self-Supervised Learning of Robust Representations

Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attack

LFAA: Crafting Transferable Targeted Adversarial Examples with Low-Frequency Perturbations

On the Robustness of Split Learning against Adversarial Attacks

Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Adversarial Color Projection: A Projector-based Physical Attack to DNNs

Adversarial Color Film: Effective Physical-World Attack to DNNs

Low-Mid Adversarial Perturbation against Unauthorized Face Recognition System