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

September 29, 2023

Adversarial Machine Learning in Latent Representations of Neural Networks
Milin Zhang, Mohammad Abdi, Francesco Restuccia
Neural Network Adversarial Attack Adversarial Robustness Adversarial Learning Latent Representation Adversarial Behavior DNN Architecture

September 28, 2023

Post-Training Overfitting Mitigation in DNN Classifiers
Hang Wang, David J. Miller, George Kesidis
Adversarial Training Adversarial Learning Model Overfitting Benign Overfitting Backdoor Poisoning Attack Deep Neural Network Classifier

September 27, 2023

September 24, 2023

September 20, 2023

Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization
Stefan Trawicki, William Hackett, Lewis Birch, Neeraj Suri, Peter Garraghan
Adversarial Learning Side Channel Model Attack Planning Based Compilation Tensor Optimization Attack Robustness

September 6, 2023

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
Takashi Shibuya, Yuhta Takida, Yuki Mitsufuji
Generative Adversarial Network Adversarial Learning Generative Adversarial Neural Vocoder Modern Vocoders

September 5, 2023

Model-based Offline Policy Optimization with Adversarial Network
Junming Yang, Xingguo Chen, Shengyuan Wang, Bolei Zhang
Offline Reinforcement Learning Adversarial Learning Offline Policy Transition Model

September 1, 2023

Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Neel Jain, Avi Schwarzschild, Yuxin Wen, Gowthami Somepalli, John Kirchenbauer, Ping-yeh Chiang, Micah Goldblum, Aniruddha Saha, Jonas Geiping, Tom Goldstein
Language Model Adversarial Attack Adversarial Training Adversarial Learning Stochastic Defense

August 27, 2023

Multi-Subdomain Adversarial Network for Cross-Subject EEG-based Emotion Recognition
Guang Lin, Jianhai Zhang
Domain Adaptation Emotion Recognition Adversarial Learning Domain Adversarial Domain Discrepancy

August 23, 2023

August 20, 2023

Adversarial Collaborative Filtering for Free
Huiyuan Chen, Xiaoting Li, Vivian Lai, Chin-Chia Michael Yeh, Yujie Fan, Yan Zheng, Mahashweta Das, Hao Yang
Adversarial Training Adversarial Perturbation Adversarial Learning Robust Recommendation

August 19, 2023

A Comparison of Adversarial Learning Techniques for Malware Detection
Pavla Louthánová, Matouš Kozák, Martin Jureček, Mark Stamp
Adversarial Attack Adversarial Learning Consistent Comparison Malware Detection Adversarial Method Malware Attack Adversarial Malware

August 7, 2023

A reading survey on adversarial machine learning: Adversarial attacks and their understanding
Shashank Kotyan
Neural Network Deep Learning Adversarial Attack Adversarial Learning Human Understanding Adversarial DEfense

August 1, 2023

Generative adversarial networks with physical sound field priors
Xenofon Karakonstantis, Efren Fernandez-Grande
Generative Model Generative Adversarial Network Adversarial Learning Generative Question Sound Field

July 31, 2023

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design
Jungil Kong, Jihoon Park, Beomjeong Kim, Jeongmin Kim, Dohee Kong, Sangjin Kim
High Efficiency Adversarial Learning Architecture Design Multi Speaker Natural Sounding Speech Single Stage

July 27, 2023

When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-$k$ Multi-Label Learning
Yuchen Sun, Qianqian Xu, Zitai Wang, Qingming Huang
Adversarial Attack Adversarial Perturbation Adversarial Learning Multi Label New Measure Imperceptible Adversarial Perturbation

July 25, 2023

Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling
Masanori Hirano, Kentaro Minami, Kentaro Imajo
Adversarial Learning Process Model Hedge Detection Deep Hedging Dynamic Hedging

Adversarial Learning

Papers

Adversarial Machine Learning in Latent Representations of Neural Networks

Post-Training Overfitting Mitigation in DNN Classifiers

On the Computational Entanglement of Distant Features in Adversarial Machine Learning

P2I-NET: Mapping Camera Pose to Image via Adversarial Learning for New View Synthesis in Real Indoor Environments

Video Adverse-Weather-Component Suppression Network via Weather Messenger and Adversarial Backpropagation

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Compilation as a Defense: Enhancing DL Model Attack Robustness via Tensor Optimization

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network

Model-based Offline Policy Optimization with Adversarial Network

Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Multi-Subdomain Adversarial Network for Cross-Subject EEG-based Emotion Recognition

A Systematic Study on Quantifying Bias in GAN-Augmented Data

Sample Complexity of Robust Learning against Evasion Attacks

Adversarial Collaborative Filtering for Free

A Comparison of Adversarial Learning Techniques for Malware Detection

A reading survey on adversarial machine learning: Adversarial attacks and their understanding

Generative adversarial networks with physical sound field priors

VITS2: Improving Quality and Efficiency of Single-Stage Text-to-Speech with Adversarial Learning and Architecture Design

When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-$k$ Multi-Label Learning

Adversarial Deep Hedging: Learning to Hedge without Price Process Modeling