Standard Adversarial Training

Standard adversarial training aims to improve the robustness of machine learning models, particularly deep neural networks, against adversarial attacks—maliciously perturbed inputs designed to cause misclassification. Current research focuses on addressing limitations of traditional adversarial training, such as robust overfitting and the computational cost, through techniques like dataset distillation, refined min-max optimization strategies (e.g., focusing on "hiders"), and novel training objectives that incorporate both adversarial and anti-adversarial examples or leverage contrastive learning. These advancements are significant because they enhance the reliability and security of machine learning systems across various applications, from image recognition to natural language processing, by mitigating vulnerabilities to adversarial attacks.

Papers

March 15, 2024

Towards Adversarially Robust Dataset Distillation by Curvature Regularization
Eric Xue, Yijiang Li, Haoyang Liu, Yifan Shen, Haohan Wang
Adversarial Robustness Dataset Distillation Adversarial Text Distilled Dataset Standard Adversarial Training Better Adversarial Robustness Curvature Regularization

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

October 4, 2023

SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers
KL Navaneet, Soroush Abbasi Koohpayegani, Essam Sleiman, Hamed Pirsiavash
Vision Transformer Deep Model Adversarial Patch Transformer Inference Standard Adversarial Training

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

May 20, 2023

Annealing Self-Distillation Rectification Improves Adversarial Training
Yu-Yu Wu, Hung-Jui Wang, Shang-Tse Chen
Adversarial Training Adversarial Robustness Adversarial Perturbation Standard Adversarial Training

April 25, 2023

Combining Adversaries with Anti-adversaries in Training
Xiaoling Zhou, Nan Yang, Ou Wu
Training Data Adversarial Training Adversarial Perturbation Multi Step Adversarial Attack Monotone Adversary Standard Adversarial Training Imbalance Learning Adversarial Direction

March 23, 2023

Generative Image Inpainting with Segmentation Confusion Adversarial Training and Contrastive Learning
Zhiwen Zuo, Lei Zhao, Ailin Li, Zhizhong Wang, Zhanjie Zhang, Jiafu Chen, Wei Xing, Dongming Lu
Contrastive Learning Adversarial Training Adversarial Framework Adversarial Game Standard Adversarial Training Generative Image

November 25, 2022

Boundary Adversarial Examples Against Adversarial Overfitting
Muhammad Zaid Hameed, Beat Buesser
Adversarial Attack Adversarial Example Adversarial Training Adversarial Learning Standard Adversarial Training

November 21, 2022

Addressing Mistake Severity in Neural Networks with Semantic Knowledge
Natalie Abreu, Nathan Vaska, Victoria Helus
Neural Network Deep Neural Network Adversarial Attack Native Robustness Semantic Knowledge Error Mitigation Standard Adversarial Training Non Robust Feature

October 20, 2022

Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models
Hannah Chen, Yangfeng Ji, David Evans
Adversarial Example Adversarial Training NLP Model Robust Training Standard Adversarial Training

August 19, 2022

DAFT: Distilling Adversarially Fine-tuned Models for Better OOD Generalization
Anshul Nasery, Sravanti Addepalli, Praneeth Netrapalli, Prateek Jain
Adversarial Training Fine Tuned Model Standard Adversarial Training

July 18, 2022

Prior-Guided Adversarial Initialization for Fast Adversarial Training
Xiaojun Jia, Yong Zhang, Xingxing Wei, Baoyuan Wu, Ke Ma, Jue Wang, Xiaochun Cao
Adversarial Attack Adversarial Example Fast Adversarial Training Fast Gradient Sign Method Standard Adversarial Training

March 28, 2022

A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness
Souvik Kundu, Sairam Sundaresan, Massoud Pedram, Peter A. Beerel
Adversarial Attack Native Robustness Adversarial Training Convolution Operation Optimal Trade Return Conditioned Supervised Learning Standard Adversarial Training

March 12, 2022

Towards Equal Opportunity Fairness through Adversarial Learning
Xudong Han, Timothy Baldwin, Trevor Cohn
Adversarial Training Adversarial Learning Bias Mitigation Adversarial Debiasing Standard Adversarial Training

February 21, 2022

Transferring Adversarial Robustness Through Robust Representation Matching
Pratik Vaishnavi, Kevin Eykholt, Amir Rahmati
Adversarial Example Adversarial Training Adversarial Robustness Robust Representation Standard Adversarial Training Representation Matching