White Box Adversarial

White-box adversarial attacks aim to evaluate and improve the robustness of machine learning models by exploiting full knowledge of the model's architecture and parameters to generate adversarial examples—inputs designed to cause misclassification. Current research focuses on developing increasingly effective white-box attacks against various model architectures, including convolutional neural networks, hypergraph neural networks, spiking neural networks, and reinforcement learning agents, and exploring defense mechanisms such as trusted execution environments and Bayesian neural networks. This research is crucial for ensuring the reliability and security of machine learning systems across diverse applications, from autonomous vehicles to healthcare and speech recognition, where vulnerabilities to adversarial attacks can have significant real-world consequences. The development of both stronger attacks and more robust defenses is driving progress in understanding and mitigating these vulnerabilities.

Papers

November 14, 2024

Enhancing generalization in high energy physics using white-box adversarial attacks
Franck Rothen, Samuel Klein, Matthew Leigh, Tobias Golling
Machine Learning Adversarial Attack Strong Generalization Supervised Learning High Energy Physic Generalization Property White Box Adversarial

October 2, 2024

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks
Rakesh Podder, Sudipto Ghosh
Convolutional Neural Network Global Impact Adversarial Threat CNN Performance White Box Adversarial Attack White Box Adversarial

September 13, 2023

Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments
Simon Queyrut, Valerio Schiavoni, Pascal Felber
Adversarial Attack Adversarial Example Self Attention Adversarial Sample Adversarial Image Trusted Execution Environment White Box Adversarial

February 24, 2023

HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks
Chao Hu, Ruishi Yu, Binqi Zeng, Yu Zhan, Ying Fu, Quan Zhang, Rongkai Liu, Heyuan Shi
Adversarial Attack Hypergraph Neural Network White Box Adversarial Attack Efficient Adversarial Attack White Box Adversarial

September 7, 2022

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples
Nuo Xu, Kaleel Mahmood, Haowen Fang, Ethan Rathbun, Caiwen Ding, Wujie Wen
Adversarial Attack Adversarial Example Spiking Neural Network Task Transferability Security Related Spike Protein White Box Adversarial

September 5, 2022

Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agents
Stephen Casper, Taylor Killian, Gabriel Kreiman, Dylan Hadfield-Menell
Adversarial Example Reinforcement Learning Agent Red Teaming Adversarial Agent Adversarial Policy White Box Adversarial

April 4, 2022

SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition
Jianfei Yang, Han Zou, Lihua Xie
Adversarial Attack Activity Recognition Black Box Adversarial Attack White Box Adversarial

March 29, 2022

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems
Nicholas Mehlman, Anirudh Sreeram, Raghuveer Peri, Shrikanth Narayanan
Adversarial Attack Speech Recognition System Image Domain Defense Method White Box Adversarial Spectral Domain Attack

March 10, 2022

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
Ye Liu, Yaya Cheng, Lianli Gao, Xianglong Liu, Qilong Zhang, Jingkuan Song
Adversarial Attack Adversarial Example Adversarial Robustness White Box Adversarial

November 16, 2021

Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks
Adaku Uchendu, Daniel Campoy, Christopher Menart, Alexandra Hildenbrandt
Native Robustness Neural Architecture Bayesian Neural Network SE SPP DenseNet Variational Bayes White Box Adversarial

White Box Adversarial

Papers

Enhancing generalization in high energy physics using white-box adversarial attacks

Impact of White-Box Adversarial Attacks on Convolutional Neural Networks

Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments

HyperAttack: Multi-Gradient-Guided White-box Adversarial Structure Attack of Hypergraph Neural Networks

Attacking the Spike: On the Transferability and Security of Spiking Neural Networks to Adversarial Examples

Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agents

SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition

Mel Frequency Spectral Domain Defenses against Adversarial Attacks on Speech Recognition Systems

Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack

Robustness of Bayesian Neural Networks to White-Box Adversarial Attacks