Robust Adversarial Learning

Robust adversarial learning aims to develop machine learning models resistant to adversarial attacks—carefully crafted inputs designed to fool the model. Current research focuses on improving model robustness against various attack types, including those in the physical world, and integrating privacy-preserving techniques like differential privacy. This field is crucial for enhancing the reliability and security of machine learning systems across diverse applications, from image classification and acoustic monitoring to medical diagnosis, where model vulnerability can have significant consequences. Ongoing efforts explore novel training algorithms and preprocessing methods to achieve a balance between robustness and standard accuracy.

Papers

January 18, 2024

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation
Janvi Thakkar, Giulio Zizzo, Sergio Maffeis
Adversarial Training Membership Inference Attack Empirical Evaluation Differentially Private Robust Adversarial Learning Simultaneous Attack Private Probabilistic

November 1, 2023

Adversarial Examples in the Physical World: A Survey
Jiakai Wang, Donghua Wang, Jin Hu, Siyang Wu, Tingsong Jiang, Wen Yao, Aishan Liu, Xianglong Liu
Timely Survey Adversarial Attack Adversarial Example Physical World Physical Adversarial Robust Adversarial Learning

August 9, 2023

Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning
Diep Luong, Minh Tran, Shayan Gharib, Konstantinos Drossos, Tuomas Virtanen
Representation Learning Source Separation Acoustic Sensing Voice Privacy Privacy Preserving Representation Robust Adversarial Learning

June 13, 2023

Theoretical Foundations of Adversarially Robust Learning
Omar Montasser
Machine Learning Adversarial Example Robust Learning Robustness Guarantee Theoretical Foundation Robust Adversarial Learning

May 25, 2023

PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation
Xianghao Jiao, Yaohua Liu, Jiaxin Gao, Xinyuan Chu, Risheng Liu, Xin Fan
Adversarial Attack Semantic Segmentation Adversarial Perturbation Image Deraining Adversarial Prediction Robust Adversarial Learning

May 20, 2022

Robust Sensible Adversarial Learning of Deep Neural Networks for Image Classification
Jungeum Kim, Xiao Wang
Deep Neural Network Adversarial Attack Native Robustness Image Classification DNN Model Robust Model Robust Adversarial Learning

Robust Adversarial Learning

Papers

Differentially Private and Adversarially Robust Machine Learning: An Empirical Evaluation

Adversarial Examples in the Physical World: A Survey

Representation Learning for Audio Privacy Preservation using Source Separation and Robust Adversarial Learning

Theoretical Foundations of Adversarially Robust Learning

PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentation

Robust Sensible Adversarial Learning of Deep Neural Networks for Image Classification