Adversarial Noise

Adversarial noise refers to carefully crafted perturbations added to data to mislead machine learning models, primarily deep neural networks. Current research focuses on detecting and mitigating these attacks across various modalities (images, audio, text), employing techniques like generative models (diffusion models), variational sparsification, and biologically-inspired feature extraction to enhance robustness. This field is crucial for ensuring the reliability and security of AI systems in diverse applications, from facial recognition and autonomous driving to medical image analysis and speech recognition, where vulnerabilities to adversarial manipulation can have significant consequences.

Papers

December 11, 2023

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity
Xudong Li, Timin Gao, Runze Hu, Yan Zhang, Shengchuan Zhang, Xiawu Zheng, Jingyuan Zheng, Yunhang Shen, Ke Li, Yutao Liu, Pingyang Dai, Rongrong Ji
Feature Selection Image Quality Adversarial Noise Reference Image Quality Assessment Nr Iqa Semantic Noise

November 22, 2023

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise
Yixin Liu, Kaidi Xu, Xun Chen, Lichao Sun
Native Robustness Adversarial Perturbation Adversarial Noise Unlearnable Example Error Minimizing Noise

October 23, 2023

F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns
Yaguan Qian, Chenyu Zhao, Zhaoquan Gu, Bin Wang, Shouling Ji, Wei Wang, Boyang Zhou, Pan Zhou
Adversarial Example Adversarial Training Adversarial Robustness Disentanglement Capability Adversarial Noise Visual Naturalness Traditional Adversarial Unintentional Perturbation

October 20, 2023

Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting
Zecheng Tang, Kaifeng Qi, Juntao Li, Min Zhang
Adversarial Attack Adversarial Example Adversarial Noise Hard Sample

October 15, 2023

AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings
Renyang Liu, Jinhong Zhang, Haoran Li, Jin Zhang, Yuanyu Wang, Wei Zhou
Adversarial Attack Adversarial Example Adversarial Noise

October 5, 2023

Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria
Nuoyan Zhou, Nannan Wang, Decheng Liu, Dawei Zhou, Xinbo Gao
Adversarial Example Adversarial Training Adversarial Robustness Alignment Problem Robust Representation Adversarial Noise Robust Representation Learning Eligibility Criterion

September 8, 2023

FIVA: Facial Image and Video Anonymization and Anonymization Defense
Felix Rosberg, Eren Erdal Aksoy, Cristofer Englund, Fernando Alonso-Fernandez
Face Image Adversarial Noise Face Swapping Reconstruction Attack Face Anonymization Image Anonymization

August 23, 2023

Efficient Transfer Learning in Diffusion Models via Adversarial Noise
Xiyu Wang, Baijiong Lin, Daochang Liu, Chang Xu
Diffusion Model Adversarial Attack Transfer Learning GAN Model Diffusion Probabilistic Model Adversarial Noise Efficient Transfer Learning

June 21, 2023

A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking
Shaohui Mei, Jiawei Lian, Xiaofei Wang, Yuru Su, Mingyang Ma, Lap-Pui Chau
Deep Neural Network Native Robustness Adversarial Robustness Image Classification Remote Sensing Benchmark Platform Adversarial Noise Intrinsic Robustness

June 13, 2023

May 28, 2023

Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness
Zhanhao Hu, Jun Zhu, Bo Zhang, Xiaolin Hu
Deep Neural Network Adversarial Example Adversarial Noise Trojan Attack Trojan Detection Physical Weakness

May 14, 2023

On enhancing the robustness of Vision Transformers: Defensive Diffusion
Raza Imam, Muhammad Huzaifa, Mohammed El-Amine Azz
Adversarial Attack Vision Transformer Native Robustness Adversarial Noise Sensitive Patient

April 27, 2023

Detection of Adversarial Physical Attacks in Time-Series Image Data
Ramneet Kaur, Yiannis Kantaros, Wenwen Si, James Weimer, Insup Lee
Adversarial Attack Data Detection Time Series Adversarial Noise Adversarial Detection

April 19, 2023

Wavelets Beat Monkeys at Adversarial Robustness
Jingtong Su, Julia Kempe
Adversarial Robustness Adversarial Noise Robust Deep Wavelet Based

March 28, 2023

Improving the Transferability of Adversarial Samples by Path-Augmented Method
Jianping Zhang, Jen-tse Huang, Wenxuan Wang, Yichen Li, Weibin Wu, Xiaosen Wang, Yuxin Su, Michael R. Lyu
Task Transferability Adversarial Sample Adversarial Noise Adversarial Data Collection Gradient Path Path Augmentation

March 17, 2023

How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?
Julia Kostin, Felix Krahmer, Dominik Stöger
Adversarial Noise Blind Deconvolution Low Rank Matrix Recovery Tensor Norm

March 9, 2023

Efficient Testable Learning of Halfspaces with Adversarial Label Noise
Ilias Diakonikolas, Daniel M. Kane, Vasilis Kontonis, Sihan Liu, Nikos Zarifis
Polynomial Time Adversarial Noise Margin Halfspaces Testable Learning

March 8, 2023

Exploring Adversarial Attacks on Neural Networks: An Explainable Approach
Justus Renkhoff, Wenkai Tan, Alvaro Velasquez, illiam Yichen Wang, Yongxin Liu, Jian Wang, Shuteng Niu, Lejla Begic Fazlic, Guido Dartmann, Houbing Song
Neural Network Deep Learning Adversarial Attack Adversarial Example Adversarial Noise Reliable Deep Learning

February 25, 2023

Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation
Shaoyan Pan, Shao-Yuan Lo, Min Huang, Chaoqiong Ma, Jacob Wynne, Tonghe Wang, Tian Liu, Xiaofeng Yang
Adversarial Attack Adversarial Noise Multi Organ Segmentation Adversarial Feature Adversarial Data Augmentation Adversarial Style Augmentation

Adversarial Noise

Papers

Adaptive Feature Selection for No-Reference Image Quality Assessment by Mitigating Semantic Noise Sensitivity

Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise

F$^2$AT: Feature-Focusing Adversarial Training via Disentanglement of Natural and Perturbed Patterns

Beyond Hard Samples: Robust and Effective Grammatical Error Correction with Cycle Self-Augmenting

AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settings

Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria

FIVA: Facial Image and Video Anonymization and Anonymization Defense

Efficient Transfer Learning in Diffusion Models via Adversarial Noise

A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking

Robustly Learning a Single Neuron via Sharpness

Malafide: a novel adversarial convolutive noise attack against deepfake and spoofing detection systems

Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness

On enhancing the robustness of Vision Transformers: Defensive Diffusion

Detection of Adversarial Physical Attacks in Time-Series Image Data

Wavelets Beat Monkeys at Adversarial Robustness

Improving the Transferability of Adversarial Samples by Path-Augmented Method

How robust is randomized blind deconvolution via nuclear norm minimization against adversarial noise?

Efficient Testable Learning of Halfspaces with Adversarial Label Noise

Exploring Adversarial Attacks on Neural Networks: An Explainable Approach

Deep Learning-based Multi-Organ CT Segmentation with Adversarial Data Augmentation