Fast Gradient Sign Method

The Fast Gradient Sign Method (FGSM) is a fast and effective adversarial attack used to evaluate the robustness of deep learning models, particularly in image classification. Current research focuses on mitigating FGSM's impact through improved defense mechanisms, including adversarial training techniques and novel preprocessing methods, often applied to various architectures like ResNets, DenseNets, and Vision Transformers. Understanding and defending against FGSM attacks is crucial for enhancing the reliability and security of machine learning systems across diverse applications, from image recognition to cybersecurity.

Papers

November 6, 2024

FedRISE: Rating Induced Sign Election of Gradients for Byzantine Tolerant Federated Aggregation
Joseph Geo Benjamin, Mothilal Asokan, Mohammad Yaqub, Karthik Nandakumar
Better Robustness Byzantine Seal Fast Gradient Sign Method Federated Aggregation Robust Aggregator

October 18, 2024

A Mirror Descent Perspective of Smoothed Sign Descent
Shuyang Wang, Diego Klabjan
Gradient Descent Mirror Descent Fast Gradient Sign Method Low Dimensional

August 20, 2024

Robust Image Classification: Defensive Strategies against FGSM and PGD Adversarial Attacks
Hetvi Waghela, Jaydip Sen, Sneha Rakshit
Adversarial Attack Adversarial Training Image Classification Adversarial Perturbation Adversarial DEfense Defense Strategy Fast Gradient Sign Method Projected Gradient Descent Attack

June 8, 2024

Adversarial flows: A gradient flow characterization of adversarial attacks
Lukas Weigand, Tim Roith, Martin Burger
Adversarial Attack Gradient Descent Gradient Flow Adversarial Text Wasserstein Gradient Fast Gradient Sign Method

April 5, 2024

Evaluating Adversarial Robustness: A Comparison Of FGSM, Carlini-Wagner Attacks, And The Role of Distillation as Defense Mechanism
Trilokesh Ranjan Sarkar, Nilanjan Das, Pralay Sankar Maitra, Bijoy Some, Ritwik Saha, Orijita Adhikary, Bishal Bose, Jaydip Sen
Deep Neural Network Adversarial Attack Adversarial Robustness Mutual Distillation DEfense Mechanism Fast Gradient Sign Method Based Attack Defensive Distillation

March 18, 2024

Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSM
Linyu Tang, Lei Zhang
Adversarial Attack Adversarial Robustness Artefact PARTICLE Adversarial Purification Robust Overfitting Fast Gradient Sign Method

December 28, 2023

Adversarial Attacks on Image Classification Models: Analysis and Defense
Jaydip Sen, Abhiraj Sen, Ananda Chatterjee
Adversarial Attack General Analysis Convolutional Neural Network Model Pre Trained Convolutional Neural Network Image Classification Model Fast Gradient Sign Method

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 26, 2023

Unscrambling the Rectification of Adversarial Attacks Transferability across Computer Networks
Ehsan Nowroozi, Samaneh Ghelichkhani, Imran Haider, Ali Dehghantanha
Convolutional Neural Network Adversarial Attack Adversarial Example Adversarial Transferability Computer Network Noise Rectification Fast Gradient Sign Method

September 4, 2023

Toward Defensive Letter Design
Rentaro Kataoka, Akisato Kimura, Seiichi Uchida
Adversarial Attack Generative Adversarial Network Adversarial Vulnerability Fast Gradient Sign Method

July 5, 2023

Adversarial Attacks on Image Classification Models: FGSM and Patch Attacks and their Impact
Jaydip Sen, Subhasis Dasgupta
Convolutional Neural Network Adversarial Attack Global Impact Pre Trained Convolutional Neural Network Adversarial Patch Attack Image Classification Model Patch Attack Fast Gradient Sign Method

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

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

May 5, 2022

Structural Extensions of Basis Pursuit: Guarantees on Adversarial Robustness
Dávid Szeghy, Mahmoud Aslan, Áron Fóthi, Balázs Mészáros, Zoltán Ádám Milacski, András Lőrincz
Adversarial Robustness Adversarial Noise Shallow Network Formal Guarantee Fast Gradient Sign Method Localized Sparse Incomplete Basis Pursuit

March 10, 2022

Attack Analysis of Face Recognition Authentication Systems Using Fast Gradient Sign Method
Arbena Musa, Kamer Vishi, Blerim Rexha
Machine Learning Face Recognition Face Verification Biometric Identification Biometric System Fast Gradient Sign Method

January 22, 2022

Robust Unpaired Single Image Super-Resolution of Faces
Saurabh Goswami, Rajagopalan A. N
Adversarial Attack Image Super Resolution Human Face Fast Gradient Sign Method

December 23, 2021

Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization
Yihua Zhang, Guanhua Zhang, Prashant Khanduri, Mingyi Hong, Shiyu Chang, Sijia Liu
Adversarial Attack Adversarial Example Adversarial Training Camera Lens Bi Level Optimization Fast Adversarial Training Fast Gradient Sign Method