Adversarial Learning

Adversarial learning is a machine learning technique that improves model robustness and fairness by pitting two neural networks against each other—a generator and a discriminator—in a competitive training process. Current research focuses on applications across diverse fields, including improving fairness in predictive analytics, enhancing robustness in reinforcement learning and domain adaptation, and mitigating the effects of adversarial attacks on various models. This approach is significant because it addresses critical limitations of standard machine learning methods, leading to more reliable and equitable outcomes in various applications, from financial risk assessment to medical image analysis and autonomous systems.

Papers

December 20, 2023

AdvST: Revisiting Data Augmentations for Single Domain Generalization
Guangtao Zheng, Mengdi Huai, Aidong Zhang
Data Augmentation Adversarial Learning Single Domain Generalization Domain Distribution Shift

December 13, 2023

Defenses in Adversarial Machine Learning: A Survey
Baoyuan Wu, Shaokui Wei, Mingli Zhu, Meixi Zheng, Zihao Zhu, Mingda Zhang, Hongrui Chen, Danni Yuan, Li Liu, Qingshan Liu
Timely Survey Adversarial Learning State of the Art Defense Attack Paradigm

December 12, 2023

December 11, 2023

Invariant Representation via Decoupling Style and Spurious Features from Images
Ruimeng Li, Yuanhao Pu, Zhaoyi Li, Hong Xie, Defu Lian
Adversarial Learning Distribution Shift Invariant Representation Multi Agent Decoupling Coefficient Spurious Feature Generalization Problem

December 7, 2023

December 6, 2023

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System
Xinwei Yuan, Shu Han, Wei Huang, Hongliang Ye, Xianglong Kong, Fan Zhang
Adversarial Attack Adversarial Robustness Adversarial Learning Intrusion Detection System

November 28, 2023

FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning
Pengchao Han, Xingyan Shi, Jianwei Huang
Knowledge Distillation Adversarial Learning Federated Distillation

November 27, 2023

High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Network
Subhajit Paul, Ashutosh Gupta
Adversarial Learning Sinkhorn Algorithm Spatial Self Attention Digital Elevation Model

November 22, 2023

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization
Yuzhe You, Jarvis Tse, Jian Zhao
Adversarial Attack Adversarial Learning Interactive Visualization Adversarial Machine Learning Red PANDA

November 16, 2023

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models
Jiongxiao Wang, Junlin Wu, Muhao Chen, Yevgeniy Vorobeychik, Chaowei Xiao
Reinforcement Learning Human Feedback Adversarial Learning Poisoning Attack RLHF V Reward Poisoning Attack Preference Poisoning

November 14, 2023

November 8, 2023

Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Muhammad Akhtar Munir, Muhammad Haris Khan, M. Saquib Sarfraz, Mohsen Ali
Adversarial Learning Object Detector Self Training Unknown Object Domain Adaptive Object Detection Class Alignment Adversarial Feature Alignment

October 28, 2023

Deep Intrinsic Decomposition with Adversarial Learning for Hyperspectral Image Classification
Zhiqiang Gong, Xian Zhou, Wen Yao
Adversarial Learning Hyperspectral Image Hyperspectral Image Classification Intrinsic Image Decomposition

October 21, 2023

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment
Chuang Zhao, Hongke Zhao, Hengshu Zhu, Zhenya Huang, Nan Feng, Enhong Chen, Hui Xiong
Unsupervised Domain Adaptation Adversarial Learning Domain Adversarial Domain Discriminator Bi Discriminator

October 10, 2023

An improved CTGAN for data processing method of imbalanced disk failure
Jingbo Jia, Peng Wu, Hussain Dawood
Adversarial Learning Data Imbalance Data Preprocessing Tabular Generative Adversarial Network Disk Failure

October 7, 2023

X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection
Lei Zhang, Hao Chen, Shu Hu, Bin Zhu, Ching Sheng Lin, Xi Wu, Jinrong Hu, Xin Wang
Generative Adversarial Network New Framework Adversarial Learning Formality Transfer Cross Entropy Loss Fake Image Deep Fake Detection

October 5, 2023

Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally
Shawqi Al-Maliki, Adnan Qayyum, Hassan Ali, Mohamed Abdallah, Junaid Qadir, Dinh Thai Hoang, Dusit Niyato, Ala Al-Fuqaha
Deep Neural Network Adversarial Example Adversarial Learning Adversary Agent Target Amazon Ally Social AI

Adversarial Learning

Papers

AdvST: Revisiting Data Augmentations for Single Domain Generalization

Defenses in Adversarial Machine Learning: A Survey

GenDet: Towards Good Generalizations for AI-Generated Image Detection

May the Noise be with you: Adversarial Training without Adversarial Examples

Invariant Representation via Decoupling Style and Spurious Features from Images

Adversarial Learning for Feature Shift Detection and Correction

Adversarial Denoising Diffusion Model for Unsupervised Anomaly Detection

A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System

FedAL: Black-Box Federated Knowledge Distillation Enabled by Adversarial Learning

High-resolution Multi-spectral Image Guided DEM Super-resolution using Sinkhorn Regularized Adversarial Network

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization

RLHFPoison: Reward Poisoning Attack for Reinforcement Learning with Human Feedback in Large Language Models

MADG: Margin-based Adversarial Learning for Domain Generalization

The Impact of Adversarial Node Placement in Decentralized Federated Learning Networks

Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning

Deep Intrinsic Decomposition with Adversarial Learning for Hyperspectral Image Classification

Bi-discriminator Domain Adversarial Neural Networks with Class-Level Gradient Alignment

An improved CTGAN for data processing method of imbalanced disk failure

X-Transfer: A Transfer Learning-Based Framework for GAN-Generated Fake Image Detection

Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally