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

November 27, 2022

November 26, 2022

Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning
Ethan Rathbun, Kaleel Mahmood, Sohaib Ahmad, Caiwen Ding, Marten van Dijk
Adversarial Attack Adversarial Example Adversarial Learning Mixture of Expert Model Attack Ensemble Adversarial Compositional Adversarial

November 25, 2022

Boundary Adversarial Examples Against Adversarial Overfitting
Muhammad Zaid Hameed, Beat Buesser
Adversarial Attack Adversarial Example Adversarial Training Adversarial Learning Standard Adversarial Training

November 24, 2022

SAGA: Spectral Adversarial Geometric Attack on 3D Meshes
Tomer Stolik, Itai Lang, Shai Avidan
Adversarial Attack 3D Mesh Segmentation and Genome Annotation Spectral Domain Attack Mesh Autoencoder Adversarial Transformation Mesh Attack

November 23, 2022

November 21, 2022

November 20, 2022

November 19, 2022

Phonemic Adversarial Attack against Audio Recognition in Real World
Jiakai Wang, Zhendong Chen, Zixin Yin, Qinghong Yang, Xianglong Liu
Adversarial Attack Fine Grained Real World Adversarial Noise Audio Recognition

November 18, 2022

November 17, 2022

Towards Good Practices in Evaluating Transfer Adversarial Attacks
Zhengyu Zhao, Hanwei Zhang, Renjue Li, Ronan Sicre, Laurent Amsaleg, Michael Backes
Adversarial Attack Best Practice Transfer Attack Transfer Based Adversarial Attack Optimal Attack

November 16, 2022

Attacking Object Detector Using A Universal Targeted Label-Switch Patch
Avishag Shapira, Ron Bitton, Dan Avraham, Alon Zolfi, Yuval Elovici, Asaf Shabtai
Adversarial Attack Object Detector Adversarial Patch Universal Image Deep Learning Based Object Label Shift Adversarial Pattern Label Attack

Adversarial Attack

Papers

Adversarial Rademacher Complexity of Deep Neural Networks

Traditional Classification Neural Networks are Good Generators: They are Competitive with DDPMs and GANs

Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning

Boundary Adversarial Examples Against Adversarial Overfitting

SAGA: Spectral Adversarial Geometric Attack on 3D Meshes

Dual Graphs of Polyhedral Decompositions for the Detection of Adversarial Attacks

Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition

Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners

Benchmarking Adversarially Robust Quantum Machine Learning at Scale

Addressing Mistake Severity in Neural Networks with Semantic Knowledge

Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization

Adversarial Cheap Talk

Invisible Backdoor Attack with Dynamic Triggers against Person Re-identification

Spectral Adversarial Training for Robust Graph Neural Network

Phonemic Adversarial Attack against Audio Recognition in Real World

Adversarial Detection by Approximation of Ensemble Boundary

Data-Adaptive Discriminative Feature Localization with Statistically Guaranteed Interpretation

Towards Good Practices in Evaluating Transfer Adversarial Attacks

Attacking Object Detector Using A Universal Targeted Label-Switch Patch