Adversarial Training Algorithm

Adversarial training aims to improve the robustness of deep neural networks against adversarial attacks, which involve subtly altering inputs to cause misclassification. Current research focuses on mitigating the trade-off between robustness and standard accuracy, exploring techniques like regularization (e.g., Fisher-Rao norm-based methods), refined min-max optimization strategies (e.g., focusing on "hiders"—previously defended samples that become vulnerable later), and incorporating unlabeled data. These advancements are crucial for deploying reliable machine learning models in safety-critical applications, where robustness to malicious inputs is paramount.

Papers

March 26, 2024

Boosting Adversarial Training via Fisher-Rao Norm-based Regularization
Xiangyu Yin, Wenjie Ruan
Adversarial Training Adversarial Robustness Adversarial Learning Adversarial Training Algorithm Fisher Rao

December 12, 2023

Focus on Hiders: Exploring Hidden Threats for Enhancing Adversarial Training
Qian Li, Yuxiao Hu, Yinpeng Dong, Dongxiao Zhang, Yuntian Chen
Adversarial Example Adversarial Training Human Driving Focus Threat Word Adversarial Training Algorithm Standard Adversarial Training Adaptive Adversarial Attack

November 29, 2023

Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
Xiaoyue Mi, Fan Tang, Yepeng Weng, Danding Wang, Juan Cao, Sheng Tang, Peng Li, Yang Liu
Adversarial Training Topological Metric Accuracy Loss Adversarial Training Algorithm

November 16, 2023

Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting
Romain Ilbert, Thai V. Hoang, Zonghua Zhang, Themis Palpanas
Adversarial Attack Native Robustness Adversarial Example System Performance Adversarial Training Algorithm Data Perturbation

August 8, 2023

Enhancing Adversarial Robustness in Low-Label Regime via Adaptively Weighted Regularization and Knowledge Distillation
Dongyoon Yang, Insung Kong, Yongdai Kim
Knowledge Distillation Adversarial Robustness Adversarial Training Algorithm Semi Supervised Adversarial

June 25, 2023

On Evaluating the Adversarial Robustness of Semantic Segmentation Models
Levente Halmosi, Mark Jelasity
Adversarial Example Adversarial Robustness Adversarial Perturbation Semantic Segmentation Model Adversarial Training Algorithm

June 19, 2023

Adversarial Training Should Be Cast as a Non-Zero-Sum Game
Alexander Robey, Fabian Latorre, George J. Pappas, Hamed Hassani, Volkan Cevher
Adversarial Training Adversarial Vulnerability Zero Sum Game Adversarial Training Algorithm Standard Adversarial Training

March 10, 2023

Do we need entire training data for adversarial training?
Vipul Gupta, Apurva Narayan
Adversarial Attack Training Data Adversarial Example Adversarial Training Adversarial Training Algorithm

March 6, 2023

Adversarial Sampling for Fairness Testing in Deep Neural Network
Tosin Ige, William Marfo, Justin Tonkinson, Sikiru Adewale, Bolanle Hafiz Matti
Deep Neural Network Adversarial Attack Adversarial Sample Adversarial Data Collection FAIrness Testing Adversarial Training Algorithm

October 27, 2022

Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
Jiachen Hu, Han Zhong, Chi Jin, Liwei Wang
Real World Environment Partial Observation Sim to Real Transfer Adversarial Training Algorithm

August 10, 2022

A Sublinear Adversarial Training Algorithm
Yeqi Gao, Lianke Qin, Zhao Song, Yitan Wang
Adversarial Attack Adversarial Training Adversarial Perturbation Two Layer Neural Network Adversarial Training Algorithm

July 20, 2022

ExoSGAN and ExoACGAN: Exoplanet Detection using Adversarial Training Algorithms
Cicy K Agnes, Akthar Naveed, Anitha Mary M O Chacko
Adversarial Training Algorithm Exoplanet Detection Semi Supervised Generative Adversarial Network

June 5, 2022

Vanilla Feature Distillation for Improving the Accuracy-Robustness Trade-Off in Adversarial Training
Guodong Cao, Zhibo Wang, Xiaowei Dong, Zhifei Zhang, Hengchang Guo, Zhan Qin, Kui Ren
Knowledge Distillation Adversarial Example Adversarial Training Adversarial Distillation Accuracy Robustness Adversarial Training Algorithm

April 28, 2022

Adversarial Fine-tune with Dynamically Regulated Adversary
Pengyue Hou, Ming Zhou, Jie Han, Petr Musilek, Xingyu Li
Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Fine Tuning Monotone Adversary Adversarial Training Algorithm

February 14, 2022

Unlabeled Data Help: Minimax Analysis and Adversarial Robustness
Yue Xing, Qifan Song, Guang Cheng
Self Supervised Learning Adversarial Robustness Minimax Optimization Adversarial Training Algorithm

February 11, 2022

Fast Adversarial Training with Noise Augmentation: A Unified Perspective on RandStart and GradAlign
Axi Niu, Kang Zhang, Chaoning Zhang, Chenshuang Zhang, In So Kweon, Chang D. Yoo, Yanning Zhang
Unified View Gradient Alignment Explicit Regularization Fast Adversarial Training Catastrophic Overfitting Adversarial Training Algorithm Noise Augmentation