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

June 11, 2023

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework
Minglei Yin, Bin Liu, Neil Zhenqiang Gong, Xin Li
Adversarial Attack Adversarial Example Man in the Middle Attack

June 9, 2023

June 8, 2023

June 6, 2023

June 5, 2023

June 4, 2023

Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy
Xiaoting Li, Lingwei Chen, Dinghao Wu
Adversarial Attack Inference Attack Adversary Agent Attribute Inference Attack Attribute Privacy

June 2, 2023

Adversarial Attack

Papers

Securing Visually-Aware Recommender Systems: An Adversarial Image Reconstruction and Detection Framework

Overcoming Adversarial Attacks for Human-in-the-Loop Applications

Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions

Adversarial Evasion Attacks Practicality in Networks: Testing the Impact of Dynamic Learning

Boosting Adversarial Transferability by Achieving Flat Local Maxima

FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs

Expanding Scope: Adapting English Adversarial Attacks to Chinese

A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions

Divide and Repair: Using Options to Improve Performance of Imitation Learning Against Adversarial Demonstrations

CFDP: Common Frequency Domain Pruning

Adversarial attacks and defenses in explainable artificial intelligence: A survey

Adversarial Attacks and Defenses for Semantic Communication in Vehicular Metaverses

Revisiting the Trade-off between Accuracy and Robustness via Weight Distribution of Filters

A Robust Likelihood Model for Novelty Detection

Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception

Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning

Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy

Poisoning Network Flow Classifiers

VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations

Adversarial Attack Based on Prediction-Correction