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

April 21, 2022

Fast AdvProp
Jieru Mei, Yucheng Han, Yutong Bai, Yixiao Zhang, Yingwei Li, Xianhang Li, Alan Yuille, Cihang Xie
Adversarial Example Adversarial Learning Adversarial Sample

April 16, 2022

Exploiting Multiple EEG Data Domains with Adversarial Learning
David Bethge, Philipp Hallgarten, Ozan Özdenizci, Ralf Mikut, Albrecht Schmidt, Tobias Grosse-Puppendahl
Emotion Recognition Adversarial Learning Domain Invariant Representation Multi Source Multi Channel EEG Source Image

April 14, 2022

PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images
Rabab Abdelfattah, Xiaofeng Wang, Song Wang
Generative Adversarial Network Semantic Segmentation Adversarial Learning Aerial Image Semantic Segmentation Network Power Line Line Detection

April 11, 2022

Ischemic Stroke Lesion Segmentation Using Adversarial Learning
Mobarakol Islam, N Rajiv Vaidyanathan, V Jeya Maria Jose, Hongliang Ren
Adversarial Learning Segmentation Network Ischemic Stroke Ischemic Stroke Lesion Segmentation

April 9, 2022

Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learning
Yangang Ren, Guojian Zhan, Liye Tang, Shengbo Eben Li, Jianhua Jiang, Jingliang Duan
Autonomous Driving Strong Generalization Autonomous Vehicle Adversarial Learning Adversarial Policy Driving Policy Signalized Intersection Dynamic Traffic

April 8, 2022

April 7, 2022

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators
Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Jiawei Han, Xia Song
Language Model Adversarial Learning Text Encoder Pre Training Model Pre Trained Text Adversarial Curriculum Training Data Generator Discriminative Sample Aware Loss Function

April 6, 2022

Adversarial Learning to Reason in an Arbitrary Logic
Stanisław J. Purgał, Cezary Kaliszyk
Reinforcement Learning Adversarial Learning Reason Giving Valued Logic Arbitrary Natural Language Text Computation Tree Logic

April 5, 2022

April 4, 2022

April 2, 2022

Learning to Simplify with Data Hopelessly Out of Alignment
Tadashi Nomoto
LeArning Abstract Raw Data GAN Model Adversarial Learning Alignment Problem Text Simplification Wasserstein Gan Sentence Alignment

March 28, 2022

Robust Unlearnable Examples: Protecting Data Against Adversarial Learning
Shaopeng Fu, Fengxiang He, Yang Liu, Li Shen, Dacheng Tao
Adversarial Training Raw Data Adversarial Learning Adversarial Loss Unlearnable Example Error Minimizing Noise

March 25, 2022

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin
Generative Model Adversarial Training Adversarial Learning Unified Alignment Adversarial Data Collection Generative Power Contrastive Energy

March 22, 2022

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain
Vision Language Model Absolute Stance Bias Contrastive Loss Adversarial Learning Bias Measurement Adversarial Debiasing Image Text Representation Prompt Programming

Adversarial Learning

Papers

Fast AdvProp

Exploiting Multiple EEG Data Domains with Adversarial Learning

PLGAN: Generative Adversarial Networks for Power-Line Segmentation in Aerial Images

Ischemic Stroke Lesion Segmentation Using Adversarial Learning

Improve Generalization of Driving Policy at Signalized Intersections with Adversarial Learning

Single-level Adversarial Data Synthesis based on Neural Tangent Kernels

Reusing the Task-specific Classifier as a Discriminator: Discriminator-free Adversarial Domain Adaptation

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Adversarial Learning to Reason in an Arbitrary Logic

Adversarial Robustness through the Lens of Convolutional Filters

Adversarial Learning of Intermediate Acoustic Feature for End-to-End Lightweight Text-to-Speech

Experimental quantum adversarial learning with programmable superconducting qubits

Robust Stuttering Detection via Multi-task and Adversarial Learning

Learning to Simplify with Data Hopelessly Out of Alignment

Semi-FairVAE: Semi-supervised Fair Representation Learning with Adversarial Variational Autoencoder

Learning Disentangled Representations of Negation and Uncertainty

Cyberbullying detection across social media platforms via platform-aware adversarial encoding

Robust Unlearnable Examples: Protecting Data Against Adversarial Learning

A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning