Fast Adversarial Training

Fast adversarial training (FAT) aims to improve the robustness of machine learning models against adversarial attacks while significantly reducing the computational cost of traditional adversarial training methods. Current research focuses on mitigating issues like catastrophic overfitting, which causes a sudden drop in model robustness, often employing techniques like adaptive loss functions, novel initialization strategies, and bi-level optimization approaches within various model architectures, including convolutional neural networks and vision transformers. These advancements are crucial for deploying robust machine learning models in safety-critical applications, particularly in areas like natural language processing and computer vision, where adversarial attacks pose significant risks.

Papers

September 26, 2024

Improving Fast Adversarial Training via Self-Knowledge Guidance
Chengze Jiang, Junkai Wang, Minjing Dong, Jie Gui, Xinli Shi, Yuan Cao, Yuan Yan Tang, James Tin-Yau Kwok
Adversarial Attack Adversarial Training Adversarial Robustness Fast Adversarial Training Self Knowledge Efficiency Robustness

August 26, 2024

TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Models
Zelin Li, Kehai Chen, Lemao Liu, Xuefeng Bai, Mingming Yang, Yang Xiang, Min Zhang
Large Language Model Adversarial Attack Fast Adversarial Training

July 22, 2024

Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspective
Jie Gui, Chengze Jiang, Minjing Dong, Kun Tong, Xinli Shi, Yuan Yan Tang, Dacheng Tao
Adversarial Example Adversarial Training Comprehensive Taxonomy Fast Adversarial Training Catastrophic Overfitting Projected Gradient Descent Attack

July 17, 2024

Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective
Zhaoxin Wang, Handing Wang, Cong Tian, Yaochu Jin
Adversarial Attack Adversarial Example Adversarial Training Bi Level Optimization Fast Algorithm Fast Adversarial Training Catastrophic Overfitting Step Attack

May 24, 2024

Efficient Adversarial Training in LLMs with Continuous Attacks
Sophie Xhonneux, Alessandro Sordoni, Stephan Günnemann, Gauthier Gidel, Leo Schwinn
Large Language Model Adversarial Attack Adversarial Training Cyber Attack Fast Adversarial Training Efficient Adversarial Training

May 1, 2024

Adversarial Attacks and Defense for Conversation Entailment Task
Zhenning Yang, Ryan Krawec, Liang-Yuan Wu
Large Language Model Adversarial Attack Textual Entailment Fast Adversarial Training Monotone Adversary

February 28, 2024

Catastrophic Overfitting: A Potential Blessing in Disguise
Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
Adversarial Example Adversarial Robustness Adversarial Data Digital STEALTH Metric Fast Adversarial Training Catastrophic Overfitting Blessing Generation

January 23, 2024

Fast Adversarial Training against Textual Adversarial Attacks
Yichen Yang, Xin Liu, Kun He
Adversarial Training Adversarial Robustness Adversarial Perturbation Textual Adversarial Attack Fast Adversarial Training

October 29, 2023

Blacksmith: Fast Adversarial Training of Vision Transformers via a Mixture of Single-step and Multi-step Methods
Mahdi Salmani, Alireza Dehghanpour Farashah, Mohammad Azizmalayeri, Mahdi Amiri, Navid Eslami, Mohammad Taghi Manzuri, Mohammad Hossein Rohban
Vision Transformer Adversarial Training Adversarial Perturbation Multi Step Novel Training Fast Adversarial Training Catastrophic Overfitting Fast Gradient Sign Method

October 16, 2023

Fast Adversarial Label-Flipping Attack on Tabular Data
Xinglong Chang, Gillian Dobbie, Jörg Wicker
Tabular Data Robust Defense Fast Adversarial Training Label Flipping Attack

October 5, 2023

Targeted Adversarial Attacks on Generalizable Neural Radiance Fields
Andras Horvath, Csaba M. Jozsa
Adversarial Attack Neural Radiance Field Adversarial Patch 3D Scene Representation Fast Adversarial Training Generalizable Neural Radiance Field

August 24, 2023

Fast Adversarial Training with Smooth Convergence
Mengnan Zhao, Lihe Zhang, Yuqiu Kong, Baocai Yin
Adversarial Robustness Fast Convergence Fast Adversarial Training Catastrophic Overfitting

August 22, 2023

Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging
Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao, Ranjie Duan, Jindong Gu, Rong Zhang, Hui Xue, Xiaochun Cao
Fast Adversarial Training Waypoint Generation WEight AVERaging Lipschitz Regularization

July 25, 2023

Imperceptible Physical Attack against Face Recognition Systems via LED Illumination Modulation
Junbin Fang, Canjian Jiang, You Jiang, Puxi Lin, Zhaojie Chen, Yujing Sun, Siu-Ming Yiu, Zoe L. Jiang
Adversarial Attack Face Recognition Fast Adversarial Training Imperceptible Attack Implant Position Illumination Modulation

May 24, 2023

Fast Adversarial CNN-based Perturbation Attack on No-Reference Image- and Video-Quality Metrics
Ekaterina Shumitskaya, Anastasia Antsiferova, Dmitriy Vatolin
Adversarial Perturbation Reference Image Fast Adversarial Training Traditional Adversarial Video Quality Metric Reference Quality Assessment Perturbation Attack Reference Quality

April 5, 2023

Hyper-parameter Tuning for Adversarially Robust Models
Pedro Mendes, Paolo Romano, David Garlan
Adversarial Training Hyper Parameter Adversarial Input Adversarial Scenario Fast Adversarial Training Hyper Parameter Tuning

April 1, 2023

Improving Fast Adversarial Training with Prior-Guided Knowledge
Xiaojun Jia, Yong Zhang, Xingxing Wei, Baoyuan Wu, Ke Ma, Jue Wang, Xiaochun Cao
Adversarial Example Adversarial Perturbation Fast Adversarial Training

February 23, 2023

Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Zhengbao He, Tao Li, Sizhe Chen, Xiaolin Huang
Adversarial Example Adversarial Training Fast Adversarial Training Catastrophic Overfitting Self Fitting Method

January 25, 2023

A Study on FGSM Adversarial Training for Neural Retrieval
Simon Lupart, Stéphane Clinchant
Adversarial Training Study Feature BERT Model Neural Information Retrieval Fast Adversarial Training Neural Retrieval

September 6, 2022

Bag of Tricks for FGSM Adversarial Training
Zichao Li, Li Liu, Zeyu Wang, Yuyin Zhou, Cihang Xie
Adversarial Training Bag Prototype Unconventional Rabbit Hat Trick Fast Adversarial Training Catastrophic Overfitting Fast Gradient Sign Method