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

July 19, 2023

Reinforcing POD-based model reduction techniques in reaction-diffusion complex networks using stochastic filtering and pattern recognition
Abhishek Ajayakumar, Soumyendu Raha
Adversarial Attack Native Robustness Neural ODE Neural Ordinary Differential Equation Pattern Recognition Complex Network Positive Reinforcement Model Reduction

July 18, 2023

Discretization-based ensemble model for robust learning in IoT
Anahita Namvar, Chandra Thapa, Salil S. Kanhere
Adversarial Attack Robust Learning Ensemble Model Internet of Thing Device IOT Technology Device Identification IoT Device Identification

July 17, 2023

July 16, 2023

On the Robustness of Split Learning against Adversarial Attacks
Mingyuan Fan, Cen Chen, Chengyu Wang, Wenmeng Zhou, Jun Huang
Adversarial Attack Native Robustness Adversarial Example Split Learning Collaborative Deep Learning Adversarial Color

July 15, 2023

July 14, 2023

July 13, 2023

July 12, 2023

Single-Class Target-Specific Attack against Interpretable Deep Learning Systems
Eldor Abdukhamidov, Mohammed Abuhamad, George K. Thiruvathukal, Hyoungshick Kim, Tamer Abuhmed
Adversarial Attack Adversarial Sample Adversarial Loss Interpretable Deep Learning Targeted Attack

July 11, 2023

Self-supervised adversarial masking for 3D point cloud representation learning
Michał Szachniewicz, Wojciech Kozłowski, Michał Stypułkowski, Maciej Zięba
Adversarial Attack Point Cloud 3D Point Cloud Point Cloud Data Adversarial Mask Point Cloud Representation Learning

July 10, 2023

Enhancing Adversarial Robustness via Score-Based Optimization
Boya Zhang, Weijian Luo, Zhihua Zhang
Adversarial Attack Adversarial Robustness Adversarial DEfense Score Based Diffusion Model Score Based

July 8, 2023

July 7, 2023

Adversarial Attack

Papers

Reinforcing POD-based model reduction techniques in reaction-diffusion complex networks using stochastic filtering and pattern recognition

Discretization-based ensemble model for robust learning in IoT

Analyzing the Impact of Adversarial Examples on Explainable Machine Learning

Adversarial Attacks on Traffic Sign Recognition: A Survey

On the Robustness of Split Learning against Adversarial Attacks

Unified Adversarial Patch for Cross-modal Attacks in the Physical World

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

RFLA: A Stealthy Reflected Light Adversarial Attack in the Physical World

On the Sensitivity of Deep Load Disaggregation to Adversarial Attacks

Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation

Vulnerability-Aware Instance Reweighting For Adversarial Training

Introducing Foundation Models as Surrogate Models: Advancing Towards More Practical Adversarial Attacks

Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations

Single-Class Target-Specific Attack against Interpretable Deep Learning Systems

Self-supervised adversarial masking for 3D point cloud representation learning

Enhancing Adversarial Robustness via Score-Based Optimization

Robust Ranking Explanations

Adversarial Self-Attack Defense and Spatial-Temporal Relation Mining for Visible-Infrared Video Person Re-Identification

A Theoretical Perspective on Subnetwork Contributions to Adversarial Robustness

Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints