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

August 23, 2023

Adversarial Training Using Feedback Loops
Ali Haisam Muhammad Rafid, Adrian Sandu
Adversarial Attack Adversarial Training Continuous Control Feedback Loop Control Architecture Adversarial Feedback

August 22, 2023

Designing an attack-defense game: how to increase robustness of financial transaction models via a competition
Alexey Zaytsev, Maria Kovaleva, Alex Natekin, Evgeni Vorsin, Valerii Smirnov, Georgii Smirnov, Oleg Sidorshin, Alexander Senin, Alexander Dudin, Dmitry Berestnev
Adversarial Attack Native Robustness Competition Platform Sequential Data

August 21, 2023

August 20, 2023

Hiding Backdoors within Event Sequence Data via Poisoning Attacks
Alina Ermilova, Elizaveta Kovtun, Dmitry Berestnev, Alexey Zaytsev
Adversarial Attack Deep Learning Model Backdoor Attack Black Box Poisoning Attack Hidden Backdoor Event Sequence Data

August 19, 2023

August 18, 2023

Backdoor Mitigation by Correcting the Distribution of Neural Activations
Xi Li, Zhen Xiang, David J. Miller, George Kesidis
Adversarial Attack Backdoor Attack Product Distribution Backdoor Trigger Neuron Activation

August 17, 2023

August 16, 2023

Benchmarking Adversarial Robustness of Compressed Deep Learning Models
Brijesh Vora, Kartik Patwari, Syed Mahbub Hafiz, Zubair Shafiq, Chen-Nee Chuah
Neural Network Adversarial Attack Adversarial Training Adversarial Robustness Adversarial Input

August 15, 2023

August 13, 2023

Adversarial Attack

Papers

Adversarial Training Using Feedback Loops

Designing an attack-defense game: how to increase robustness of financial transaction models via a competition

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

Enhancing Adversarial Attacks: The Similar Target Method

On the Adversarial Robustness of Multi-Modal Foundation Models

Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models

Hiding Backdoors within Event Sequence Data via Poisoning Attacks

A Comparison of Adversarial Learning Techniques for Malware Detection

Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method

Backdoor Mitigation by Correcting the Distribution of Neural Activations

Towards a Practical Defense against Adversarial Attacks on Deep Learning-based Malware Detectors via Randomized Smoothing

AIR: Threats of Adversarial Attacks on Deep Learning-Based Information Recovery

Benchmarking Adversarial Robustness of Compressed Deep Learning Models

A Review of Adversarial Attacks in Computer Vision

Enhancing the Antidote: Improved Pointwise Certifications against Poisoning Attacks

SoK: Realistic Adversarial Attacks and Defenses for Intelligent Network Intrusion Detection

Robust Infidelity: When Faithfulness Measures on Masked Language Models Are Misleading

DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning

On the Interplay of Convolutional Padding and Adversarial Robustness

Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks