Gradient Based Attack

Gradient-based attacks exploit the gradients of machine learning models to generate adversarial examples—inputs subtly modified to cause misclassification. Current research focuses on improving attack effectiveness and transferability across different models and datasets, exploring techniques like momentum acceleration, hyperparameter optimization, and novel loss functions within various architectures (e.g., Graph Neural Networks, Large Language Models, and image classifiers). Understanding and mitigating the vulnerability of models to these attacks is crucial for ensuring the reliability and security of machine learning systems in diverse applications, from autonomous driving to healthcare.

Papers

June 2, 2023

Adversarial Attack Based on Prediction-Correction
Chen Wan, Fangjun Huang
Adversarial Attack Adversarial Example Gradient Based Attack

March 27, 2023

Improving the Transferability of Adversarial Examples via Direction Tuning
Xiangyuan Yang, Jie Lin, Hanlin Zhang, Xinyu Yang, Peng Zhao
Adversarial Example Task Transferability Gradient Based Attack Transfer Attack Transfer Based Adversarial Attack

February 10, 2023

Step by Step Loss Goes Very Far: Multi-Step Quantization for Adversarial Text Attacks
Piotr Gaiński, Klaudia Bałazy
Adversarial Example Transformer Based Language Model Text Representation Cross Over Step Adversarial Loss Gradient Based Attack Textual Adversarial Attack Step Count

October 20, 2022

Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient Matching
Cangxiong Chen, Neill D. F. Campbell
Gradient Based Attack Linear System Gradient Matching Gradient Leakage Attack Training Data Leakage

October 15, 2022

Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability
Zhao Song, Yitan Wang, Zheng Yu, Lichen Zhang
Efficient Algorithm Hand Drawn Sketch Latent Vulnerability Gradient Information Gradient Based Attack Gradient Leakage First Order Method Sketching System Low Bitrates

August 26, 2022

What Does the Gradient Tell When Attacking the Graph Structure
Zihan Liu, Ge Wang, Yun Luo, Stan Z. Li
Graph Neural Network Adversarial Attack Natural Gradient Graph Structure Gradient Based Attack Node Similarity Inter Class

July 13, 2022

On the Robustness of Bayesian Neural Networks to Adversarial Attacks
Luca Bortolussi, Ginevra Carbone, Luca Laurenti, Andrea Patane, Guido Sanguinetti, Matthew Wicker
Adversarial Attack Native Robustness Variational Inference Bayesian Neural Network Gradient Based Attack

June 9, 2022

ReFace: Real-time Adversarial Attacks on Face Recognition Systems
Shehzeen Hussain, Todd Huster, Chris Mesterharm, Paarth Neekhara, Kevin An, Malhar Jere, Harshvardhan Sikka, Farinaz Koushanfar
Adversarial Example Adversarial Perturbation Gradient Based Attack G ReFine Adversarial Transformation

May 19, 2022

Focused Adversarial Attacks
Thomas Cilloni, Charles Walter, Charles Fleming
Adversarial Attack Adversarial Example Adversarial Method Gradient Based Attack Gradient Based Adversarial

April 6, 2022

Sampling-based Fast Gradient Rescaling Method for Highly Transferable Adversarial Attacks
Xu Han, Anmin Liu, Yifeng Xiong, Yanbo Fan, Kun He
Adversarial Example Practical Method Transferable Adversarial Attack Gradient Based Attack Gradient Update Fast Gradient

March 24, 2022

MERLIN -- Malware Evasion with Reinforcement LearnINg
Tony Quertier, Benjamin Marais, Stéphane Morucci, Bertrand Fournel
Reinforcement Learning Machine Learning Malware Detection Gradient Based Attack Two Memory Reinforcement

February 2, 2022

An Eye for an Eye: Defending against Gradient-based Attacks with Gradients
Hanbin Hong, Yuan Hong, Yu Kong
Adversarial Attack Adversarial Image Human Eye Gradient Based Attack Stream Network

January 12, 2022

Adversarially Robust Classification by Conditional Generative Model Inversion
Mitra Alirezaei, Tolga Tasdizen
Adversarial Attack Generative Adversarial Network Adversarial Training Gradient Based Attack Robust Classification Adversarial Defense Generative Model Inversion

December 11, 2021

Improving the Transferability of Adversarial Examples with Resized-Diverse-Inputs, Diversity-Ensemble and Region Fitting
Junhua Zou, Zhisong Pan, Junyang Qiu, Xin Liu, Ting Rui, Wei Li
Adversarial Example Task Transferability Gradient Based Attack Region Prediction Resized Diverse Input

December 2, 2021

November 27, 2021

Adaptive Perturbation for Adversarial Attack
Zheng Yuan, Jie Zhang, Zhaoyan Jiang, Liangliang Li, Shiguang Shan
Adversarial Attack Adversarial Example Adversarial Perturbation Gradient Based Attack Exact Gradient Targeted Perturbation Sign Function

November 19, 2021

Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification
Cangxiong Chen, Neill D. F. Campbell
Neural Network Deep Learning Model Image Classification Deep Network Gradient Based Attack Training Data Leakage

November 15, 2021

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks
Chen Ma, Xiangyu Guo, Li Chen, Jun-Hai Yong, Yisen Wang
Adversarial Attack Gradient Based Attack Distortion Realism Hard Label Attack

November 8, 2021

Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks
Lijia Yu, Xiao-Shan Gao
Adversarial Attack Robust Version DNN Framework Gradient Based Attack Biased Classifier Safety Classifier