Adversarial Example

Adversarial examples are subtly altered inputs designed to fool machine learning models, primarily deep neural networks (DNNs), into making incorrect predictions. Current research focuses on improving model robustness against these attacks, exploring techniques like ensemble methods, multi-objective representation learning, and adversarial training, often applied to architectures such as ResNets and Vision Transformers. Understanding and mitigating the threat of adversarial examples is crucial for ensuring the reliability and security of AI systems across diverse applications, from image classification and natural language processing to malware detection and autonomous driving. The development of robust defenses and effective attack detection methods remains a significant area of ongoing investigation.

Papers

November 30, 2021

Using a GAN to Generate Adversarial Examples to Facial Image Recognition
Andrew Merrigan, Alan F. Smeaton
Generative Adversarial Network Adversarial Example Face Recognition

November 27, 2021

November 26, 2021

Simple Contrastive Representation Adversarial Learning for NLP Tasks
Deshui Miao, Jiaqi Zhang, Wenbo Xie, Jian Song, Xin Li, Lijuan Jia, Ning Guo
Contrastive Learning Adversarial Example Adversarial Training Contrastive Loss NLP Task Adversarial Contrastive Learning Adversarial Contrastive

November 25, 2021

November 24, 2021

November 23, 2021

Adversarial machine learning for protecting against online manipulation
Stefano Cresci, Marinella Petrocchi, Angelo Spognardi, Stefano Tognazzi
Adversarial Example Adversarial Learning Image Recognition Social Bot Detection Market Manipulation Hybrid Attack

November 22, 2021

November 19, 2021

November 18, 2021

November 16, 2021

Detecting AutoAttack Perturbations in the Frequency Domain
Peter Lorenz, Paula Harder, Dominik Strassel, Margret Keuper, Janis Keuper
Adversarial Attack Adversarial Example Adversarial Training Frequency Domain Attack Detection

November 14, 2021

Generating Band-Limited Adversarial Surfaces Using Neural Networks
Roee Ben-Shlomo, Yevgeniy Men, Ido Imanuel
Neural Network Adversarial Attack Adversarial Example PointNet Model Adversarial Generation

Adversarial Example

Papers

Using a GAN to Generate Adversarial Examples to Facial Image Recognition

Adaptive Image Transformations for Transfer-based Adversarial Attack

Adaptive Perturbation for Adversarial Attack

Simple Contrastive Representation Adversarial Learning for NLP Tasks

Clustering Effect of (Linearized) Adversarial Robust Models

Robustness against Adversarial Attacks in Neural Networks using Incremental Dissipativity

Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approaches

Thundernna: a white box adversarial attack

Adversarial machine learning for protecting against online manipulation

Adversarial Examples on Segmentation Models Can be Easy to Transfer

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes

Medical Aegis: Robust adversarial protectors for medical images

Meta Adversarial Perturbations

Enhanced countering adversarial attacks via input denoising and feature restoring

Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method

TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems

A Review of Adversarial Attack and Defense for Classification Methods

How to Build Robust FAQ Chatbot with Controllable Question Generator?

Detecting AutoAttack Perturbations in the Frequency Domain

Generating Band-Limited Adversarial Surfaces Using Neural Networks