Adversarial Attack

Adversarial attacks aim to deceive machine learning models by subtly altering input data, causing misclassifications or other erroneous outputs. Current research focuses on developing more robust models and detection methods, exploring various attack strategies across different model architectures (including vision transformers, recurrent neural networks, and graph neural networks) and data types (images, text, signals, and tabular data). Understanding and mitigating these attacks is crucial for ensuring the reliability and security of AI systems in diverse applications, from autonomous vehicles to medical diagnosis and cybersecurity.

Papers

April 4, 2023

April 1, 2023

GradMDM: Adversarial Attack on Dynamic Networks
Jianhong Pan, Lin Geng Foo, Qichen Zheng, Zhipeng Fan, Hossein Rahmani, Qiuhong Ke, Jun Liu
Adversarial Attack Native Robustness Dynamic Network Dynamic Neural Network

March 31, 2023

Towards Adversarially Robust Continual Learning
Tao Bai, Chen Chen, Lingjuan Lyu, Jun Zhao, Bihan Wen
Adversarial Attack Continual LEArning Adversarial Training Adversarial Robustness Continual Learning Model Continual Adversarial Defense

March 30, 2023

Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness
Timothy Redgrave, Colton Crum
Adversarial Attack Adversarial Robustness Adversarial Sample Mini Batch Adversarial Data Collection

March 29, 2023

March 28, 2023

March 27, 2023

March 25, 2023

March 24, 2023

Adversarial Attack

Papers

Cross-Class Feature Augmentation for Class Incremental Learning

NetFlick: Adversarial Flickering Attacks on Deep Learning Based Video Compression

GradMDM: Adversarial Attack on Dynamic Networks

Towards Adversarially Robust Continual Learning

Generating Adversarial Samples in Mini-Batches May Be Detrimental To Adversarial Robustness

Targeted Adversarial Attacks on Wind Power Forecasts

A Pilot Study of Query-Free Adversarial Attack against Stable Diffusion

A Survey on Malware Detection with Graph Representation Learning

Denoising Autoencoder-based Defensive Distillation as an Adversarial Robustness Algorithm

Machine-learned Adversarial Attacks against Fault Prediction Systems in Smart Electrical Grids

Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition

EMShepherd: Detecting Adversarial Samples via Side-channel Leakage

Classifier Robustness Enhancement Via Test-Time Transformation

Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection

Improving robustness of jet tagging algorithms with adversarial training: exploring the loss surface

Ensemble-based Blackbox Attacks on Dense Prediction

Adversarial Attack and Defense for Medical Image Analysis: Methods and Applications

Improved Adversarial Training Through Adaptive Instance-wise Loss Smoothing

PIAT: Parameter Interpolation based Adversarial Training for Image Classification

Effective black box adversarial attack with handcrafted kernels